Upload 40 files

adapter_config.json

@@ -9,8 +9,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
+  "lora_alpha": 24,
+  "lora_dropout": 0.01,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9b71ca65f606945477ef5cc8f216bbed6dc0e9d370e208158c05099c7dcf627
+oid sha256:7d9b9026f1fc8d65193982e5cb561167c3246717663d8f0465fa4bb4d1521817
 size 1789320

checkpoint-1500/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: yhavinga/t5-base-dutch
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

checkpoint-1500/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "yhavinga/t5-base-dutch",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 24,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad6d9dba1912db8fa6770590fc57c78290edbb76e2de891b716ad19af8a71672
+size 1789320

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ae103f6c66c700acd83415a40f6041d14009d5558f17eb54d5085e5c4729de1
+size 3624250

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac1aeb05db14121ae77069110dba6be929bcba24e5503dfcd1721dd50a13174c
+size 14244

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdf7a26f114c1028889c9ee87ee3f62b33676a571daea78e3ac09e6754d96f61
+size 1064

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,937 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32100": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32101": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32102": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1459 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 109.0909090909091,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "eval_gen_len": 13.1091,
+      "eval_loss": 21.40757179260254,
+      "eval_rouge1": 0.0745,
+      "eval_rouge2": 0.0159,
+      "eval_rougeL": 0.0584,
+      "eval_rougeLsum": 0.0582,
+      "eval_runtime": 11.5492,
+      "eval_samples_per_second": 9.524,
+      "eval_steps_per_second": 1.212,
+      "step": 13
+    },
+    {
+      "epoch": 1.96,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.254241943359375,
+      "eval_rouge1": 0.0726,
+      "eval_rouge2": 0.0153,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5424,
+      "eval_samples_per_second": 11.528,
+      "eval_steps_per_second": 1.467,
+      "step": 27
+    },
+    {
+      "epoch": 2.98,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.031164169311523,
+      "eval_rouge1": 0.0724,
+      "eval_rouge2": 0.0176,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5313,
+      "eval_samples_per_second": 11.541,
+      "eval_steps_per_second": 1.469,
+      "step": 41
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 12.6727,
+      "eval_loss": 20.743330001831055,
+      "eval_rouge1": 0.0722,
+      "eval_rouge2": 0.0175,
+      "eval_rougeL": 0.055,
+      "eval_rougeLsum": 0.0551,
+      "eval_runtime": 9.5638,
+      "eval_samples_per_second": 11.502,
+      "eval_steps_per_second": 1.464,
+      "step": 55
+    },
+    {
+      "epoch": 4.95,
+      "eval_gen_len": 12.5273,
+      "eval_loss": 20.430522918701172,
+      "eval_rouge1": 0.0708,
+      "eval_rouge2": 0.0177,
+      "eval_rougeL": 0.0545,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.583,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 68
+    },
+    {
+      "epoch": 5.96,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 20.10591697692871,
+      "eval_rouge1": 0.0725,
+      "eval_rouge2": 0.0185,
+      "eval_rougeL": 0.0559,
+      "eval_rougeLsum": 0.0559,
+      "eval_runtime": 9.5892,
+      "eval_samples_per_second": 11.471,
+      "eval_steps_per_second": 1.46,
+      "step": 82
+    },
+    {
+      "epoch": 6.98,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 19.850391387939453,
+      "eval_rouge1": 0.0727,
+      "eval_rouge2": 0.0169,
+      "eval_rougeL": 0.0551,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.6928,
+      "eval_samples_per_second": 11.349,
+      "eval_steps_per_second": 1.444,
+      "step": 96
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.628494262695312,
+      "eval_rouge1": 0.0816,
+      "eval_rouge2": 0.0228,
+      "eval_rougeL": 0.062,
+      "eval_rougeLsum": 0.0622,
+      "eval_runtime": 9.7244,
+      "eval_samples_per_second": 11.312,
+      "eval_steps_per_second": 1.44,
+      "step": 110
+    },
+    {
+      "epoch": 8.95,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.41258430480957,
+      "eval_rouge1": 0.0811,
+      "eval_rouge2": 0.0214,
+      "eval_rougeL": 0.0613,
+      "eval_rougeLsum": 0.0614,
+      "eval_runtime": 9.5996,
+      "eval_samples_per_second": 11.459,
+      "eval_steps_per_second": 1.458,
+      "step": 123
+    },
+    {
+      "epoch": 9.96,
+      "eval_gen_len": 13.5182,
+      "eval_loss": 19.160032272338867,
+      "eval_rouge1": 0.0818,
+      "eval_rouge2": 0.0208,
+      "eval_rougeL": 0.0632,
+      "eval_rougeLsum": 0.0633,
+      "eval_runtime": 9.5959,
+      "eval_samples_per_second": 11.463,
+      "eval_steps_per_second": 1.459,
+      "step": 137
+    },
+    {
+      "epoch": 10.98,
+      "eval_gen_len": 13.8909,
+      "eval_loss": 18.8905086517334,
+      "eval_rouge1": 0.09,
+      "eval_rouge2": 0.024,
+      "eval_rougeL": 0.0698,
+      "eval_rougeLsum": 0.0696,
+      "eval_runtime": 9.6532,
+      "eval_samples_per_second": 11.395,
+      "eval_steps_per_second": 1.45,
+      "step": 151
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 14.1818,
+      "eval_loss": 18.593591690063477,
+      "eval_rouge1": 0.094,
+      "eval_rouge2": 0.0324,
+      "eval_rougeL": 0.0735,
+      "eval_rougeLsum": 0.0732,
+      "eval_runtime": 9.6893,
+      "eval_samples_per_second": 11.353,
+      "eval_steps_per_second": 1.445,
+      "step": 165
+    },
+    {
+      "epoch": 12.95,
+      "eval_gen_len": 14.4364,
+      "eval_loss": 18.286243438720703,
+      "eval_rouge1": 0.0928,
+      "eval_rouge2": 0.0329,
+      "eval_rougeL": 0.0746,
+      "eval_rougeLsum": 0.0749,
+      "eval_runtime": 9.7163,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.441,
+      "step": 178
+    },
+    {
+      "epoch": 13.96,
+      "eval_gen_len": 15.0727,
+      "eval_loss": 17.896913528442383,
+      "eval_rouge1": 0.096,
+      "eval_rouge2": 0.0328,
+      "eval_rougeL": 0.0788,
+      "eval_rougeLsum": 0.0792,
+      "eval_runtime": 9.6929,
+      "eval_samples_per_second": 11.348,
+      "eval_steps_per_second": 1.444,
+      "step": 192
+    },
+    {
+      "epoch": 14.98,
+      "eval_gen_len": 15.7364,
+      "eval_loss": 17.442358016967773,
+      "eval_rouge1": 0.1015,
+      "eval_rouge2": 0.0334,
+      "eval_rougeL": 0.0816,
+      "eval_rougeLsum": 0.0818,
+      "eval_runtime": 9.6767,
+      "eval_samples_per_second": 11.368,
+      "eval_steps_per_second": 1.447,
+      "step": 206
+    },
+    {
+      "epoch": 16.0,
+      "eval_gen_len": 16.2364,
+      "eval_loss": 16.91552734375,
+      "eval_rouge1": 0.1001,
+      "eval_rouge2": 0.0337,
+      "eval_rougeL": 0.0811,
+      "eval_rougeLsum": 0.0814,
+      "eval_runtime": 9.5645,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 220
+    },
+    {
+      "epoch": 16.95,
+      "eval_gen_len": 16.6818,
+      "eval_loss": 16.372838973999023,
+      "eval_rouge1": 0.102,
+      "eval_rouge2": 0.0336,
+      "eval_rougeL": 0.081,
+      "eval_rougeLsum": 0.0809,
+      "eval_runtime": 9.7488,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 1.436,
+      "step": 233
+    },
+    {
+      "epoch": 17.96,
+      "eval_gen_len": 16.5364,
+      "eval_loss": 15.727865219116211,
+      "eval_rouge1": 0.0901,
+      "eval_rouge2": 0.0301,
+      "eval_rougeL": 0.0739,
+      "eval_rougeLsum": 0.0741,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 247
+    },
+    {
+      "epoch": 18.98,
+      "eval_gen_len": 16.9818,
+      "eval_loss": 14.980103492736816,
+      "eval_rouge1": 0.0828,
+      "eval_rouge2": 0.0258,
+      "eval_rougeL": 0.0673,
+      "eval_rougeLsum": 0.0671,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 261
+    },
+    {
+      "epoch": 20.0,
+      "eval_gen_len": 16.4727,
+      "eval_loss": 14.11096477508545,
+      "eval_rouge1": 0.0687,
+      "eval_rouge2": 0.0146,
+      "eval_rougeL": 0.0549,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.556,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 275
+    },
+    {
+      "epoch": 20.95,
+      "eval_gen_len": 14.2364,
+      "eval_loss": 13.337847709655762,
+      "eval_rouge1": 0.051,
+      "eval_rouge2": 0.0102,
+      "eval_rougeL": 0.0418,
+      "eval_rougeLsum": 0.0414,
+      "eval_runtime": 9.7157,
+      "eval_samples_per_second": 11.322,
+      "eval_steps_per_second": 1.441,
+      "step": 288
+    },
+    {
+      "epoch": 21.96,
+      "eval_gen_len": 12.3818,
+      "eval_loss": 12.585112571716309,
+      "eval_rouge1": 0.0377,
+      "eval_rouge2": 0.007,
+      "eval_rougeL": 0.0317,
+      "eval_rougeLsum": 0.0317,
+      "eval_runtime": 9.5457,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 302
+    },
+    {
+      "epoch": 22.98,
+      "eval_gen_len": 12.0455,
+      "eval_loss": 11.860977172851562,
+      "eval_rouge1": 0.023,
+      "eval_rouge2": 0.0048,
+      "eval_rougeL": 0.0204,
+      "eval_rougeLsum": 0.0204,
+      "eval_runtime": 9.5524,
+      "eval_samples_per_second": 11.515,
+      "eval_steps_per_second": 1.466,
+      "step": 316
+    },
+    {
+      "epoch": 24.0,
+      "eval_gen_len": 10.8545,
+      "eval_loss": 11.155168533325195,
+      "eval_rouge1": 0.012,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0108,
+      "eval_rougeLsum": 0.0108,
+      "eval_runtime": 9.5834,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 330
+    },
+    {
+      "epoch": 24.95,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 10.512735366821289,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0035,
+      "eval_rougeLsum": 0.0036,
+      "eval_runtime": 9.613,
+      "eval_samples_per_second": 11.443,
+      "eval_steps_per_second": 1.456,
+      "step": 343
+    },
+    {
+      "epoch": 25.96,
+      "eval_gen_len": 11.6,
+      "eval_loss": 9.83348560333252,
+      "eval_rouge1": 0.0039,
+      "eval_rouge2": 0.0002,
+      "eval_rougeL": 0.0038,
+      "eval_rougeLsum": 0.0039,
+      "eval_runtime": 9.5253,
+      "eval_samples_per_second": 11.548,
+      "eval_steps_per_second": 1.47,
+      "step": 357
+    },
+    {
+      "epoch": 26.98,
+      "eval_gen_len": 13.0455,
+      "eval_loss": 9.216172218322754,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5441,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 371
+    },
+    {
+      "epoch": 28.0,
+      "eval_gen_len": 14.6818,
+      "eval_loss": 8.572382926940918,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6018,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 385
+    },
+    {
+      "epoch": 28.95,
+      "eval_gen_len": 15.2727,
+      "eval_loss": 8.037731170654297,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0009,
+      "eval_rougeLsum": 0.0009,
+      "eval_runtime": 9.5646,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 398
+    },
+    {
+      "epoch": 29.96,
+      "eval_gen_len": 16.3909,
+      "eval_loss": 7.415070056915283,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5548,
+      "eval_samples_per_second": 11.513,
+      "eval_steps_per_second": 1.465,
+      "step": 412
+    },
+    {
+      "epoch": 30.98,
+      "eval_gen_len": 17.8364,
+      "eval_loss": 6.802865028381348,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5629,
+      "eval_samples_per_second": 11.503,
+      "eval_steps_per_second": 1.464,
+      "step": 426
+    },
+    {
+      "epoch": 32.0,
+      "eval_gen_len": 18.2818,
+      "eval_loss": 6.211207866668701,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 440
+    },
+    {
+      "epoch": 32.95,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.717328071594238,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.505,
+      "eval_samples_per_second": 11.573,
+      "eval_steps_per_second": 1.473,
+      "step": 453
+    },
+    {
+      "epoch": 33.96,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.17288064956665,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5443,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 467
+    },
+    {
+      "epoch": 34.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.669548034667969,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4845,
+      "eval_samples_per_second": 11.598,
+      "eval_steps_per_second": 1.476,
+      "step": 481
+    },
+    {
+      "epoch": 36.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.216309547424316,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5515,
+      "eval_samples_per_second": 11.516,
+      "eval_steps_per_second": 1.466,
+      "step": 495
+    },
+    {
+      "epoch": 36.36,
+      "grad_norm": 5.376431465148926,
+      "learning_rate": 1.660854700854701e-05,
+      "loss": 14.4939,
+      "step": 500
+    },
+    {
+      "epoch": 36.95,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.8450570106506348,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 508
+    },
+    {
+      "epoch": 37.96,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.507812261581421,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5902,
+      "eval_samples_per_second": 11.47,
+      "eval_steps_per_second": 1.46,
+      "step": 522
+    },
+    {
+      "epoch": 38.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.231505870819092,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5074,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 536
+    },
+    {
+      "epoch": 40.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.9967288970947266,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5195,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 550
+    },
+    {
+      "epoch": 40.95,
+      "eval_gen_len": 18.9545,
+      "eval_loss": 2.8089849948883057,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5224,
+      "eval_samples_per_second": 11.552,
+      "eval_steps_per_second": 1.47,
+      "step": 563
+    },
+    {
+      "epoch": 41.96,
+      "eval_gen_len": 18.3727,
+      "eval_loss": 2.6384663581848145,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5129,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 577
+    },
+    {
+      "epoch": 42.98,
+      "eval_gen_len": 16.7273,
+      "eval_loss": 2.492598295211792,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5174,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 591
+    },
+    {
+      "epoch": 44.0,
+      "eval_gen_len": 11.9636,
+      "eval_loss": 2.3677501678466797,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5796,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 605
+    },
+    {
+      "epoch": 44.95,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 2.2777955532073975,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6685,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 618
+    },
+    {
+      "epoch": 45.96,
+      "eval_gen_len": 7.9455,
+      "eval_loss": 2.198147773742676,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.585,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 632
+    },
+    {
+      "epoch": 46.98,
+      "eval_gen_len": 7.5909,
+      "eval_loss": 2.1306562423706055,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6008,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.458,
+      "step": 646
+    },
+    {
+      "epoch": 48.0,
+      "eval_gen_len": 7.4091,
+      "eval_loss": 2.0773117542266846,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.6506,
+      "eval_samples_per_second": 11.398,
+      "eval_steps_per_second": 1.451,
+      "step": 660
+    },
+    {
+      "epoch": 48.95,
+      "eval_gen_len": 7.2909,
+      "eval_loss": 2.036808729171753,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5097,
+      "eval_samples_per_second": 11.567,
+      "eval_steps_per_second": 1.472,
+      "step": 673
+    },
+    {
+      "epoch": 49.96,
+      "eval_gen_len": 6.8364,
+      "eval_loss": 1.9949748516082764,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6031,
+      "eval_samples_per_second": 11.455,
+      "eval_steps_per_second": 1.458,
+      "step": 687
+    },
+    {
+      "epoch": 50.98,
+      "eval_gen_len": 7.8273,
+      "eval_loss": 1.957520842552185,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 701
+    },
+    {
+      "epoch": 52.0,
+      "eval_gen_len": 7.5545,
+      "eval_loss": 1.9219788312911987,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5836,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 715
+    },
+    {
+      "epoch": 52.95,
+      "eval_gen_len": 7.5364,
+      "eval_loss": 1.8916202783584595,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 728
+    },
+    {
+      "epoch": 53.96,
+      "eval_gen_len": 7.1182,
+      "eval_loss": 1.8674402236938477,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5024,
+      "eval_samples_per_second": 11.576,
+      "eval_steps_per_second": 1.473,
+      "step": 742
+    },
+    {
+      "epoch": 54.98,
+      "eval_gen_len": 7.0364,
+      "eval_loss": 1.846158742904663,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 756
+    },
+    {
+      "epoch": 56.0,
+      "eval_gen_len": 7.0,
+      "eval_loss": 1.827086329460144,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.591,
+      "eval_samples_per_second": 11.469,
+      "eval_steps_per_second": 1.46,
+      "step": 770
+    },
+    {
+      "epoch": 56.95,
+      "eval_gen_len": 7.5455,
+      "eval_loss": 1.8088210821151733,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.572,
+      "eval_samples_per_second": 11.492,
+      "eval_steps_per_second": 1.463,
+      "step": 783
+    },
+    {
+      "epoch": 57.96,
+      "eval_gen_len": 7.9,
+      "eval_loss": 1.789602279663086,
+      "eval_rouge1": 0.0001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0001,
+      "eval_rougeLsum": 0.0001,
+      "eval_runtime": 9.5837,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 797
+    },
+    {
+      "epoch": 58.98,
+      "eval_gen_len": 8.2545,
+      "eval_loss": 1.7687013149261475,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6152,
+      "eval_samples_per_second": 11.44,
+      "eval_steps_per_second": 1.456,
+      "step": 811
+    },
+    {
+      "epoch": 60.0,
+      "eval_gen_len": 8.3636,
+      "eval_loss": 1.7496564388275146,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4902,
+      "eval_samples_per_second": 11.591,
+      "eval_steps_per_second": 1.475,
+      "step": 825
+    },
+    {
+      "epoch": 60.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.7332907915115356,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 838
+    },
+    {
+      "epoch": 61.96,
+      "eval_gen_len": 8.9,
+      "eval_loss": 1.7185932397842407,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4797,
+      "eval_samples_per_second": 11.604,
+      "eval_steps_per_second": 1.477,
+      "step": 852
+    },
+    {
+      "epoch": 62.98,
+      "eval_gen_len": 9.7545,
+      "eval_loss": 1.7047526836395264,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.618,
+      "eval_samples_per_second": 11.437,
+      "eval_steps_per_second": 1.456,
+      "step": 866
+    },
+    {
+      "epoch": 64.0,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 1.6921414136886597,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6264,
+      "eval_samples_per_second": 11.427,
+      "eval_steps_per_second": 1.454,
+      "step": 880
+    },
+    {
+      "epoch": 64.95,
+      "eval_gen_len": 9.6909,
+      "eval_loss": 1.6816327571868896,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5134,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 893
+    },
+    {
+      "epoch": 65.96,
+      "eval_gen_len": 8.9545,
+      "eval_loss": 1.6697723865509033,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5506,
+      "eval_samples_per_second": 11.518,
+      "eval_steps_per_second": 1.466,
+      "step": 907
+    },
+    {
+      "epoch": 66.98,
+      "eval_gen_len": 9.6818,
+      "eval_loss": 1.6568113565444946,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 921
+    },
+    {
+      "epoch": 68.0,
+      "eval_gen_len": 9.9455,
+      "eval_loss": 1.6469463109970093,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4825,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 935
+    },
+    {
+      "epoch": 68.95,
+      "eval_gen_len": 9.3545,
+      "eval_loss": 1.6408612728118896,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5212,
+      "eval_samples_per_second": 11.553,
+      "eval_steps_per_second": 1.47,
+      "step": 948
+    },
+    {
+      "epoch": 69.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.6316603422164917,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4986,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 962
+    },
+    {
+      "epoch": 70.98,
+      "eval_gen_len": 9.7818,
+      "eval_loss": 1.623169183731079,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5276,
+      "eval_samples_per_second": 11.545,
+      "eval_steps_per_second": 1.469,
+      "step": 976
+    },
+    {
+      "epoch": 72.0,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 1.6152759790420532,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5801,
+      "eval_samples_per_second": 11.482,
+      "eval_steps_per_second": 1.461,
+      "step": 990
+    },
+    {
+      "epoch": 72.73,
+      "grad_norm": 3.344996213912964,
+      "learning_rate": 1.3196581196581197e-05,
+      "loss": 2.6089,
+      "step": 1000
+    },
+    {
+      "epoch": 72.95,
+      "eval_gen_len": 9.1727,
+      "eval_loss": 1.6071548461914062,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.6124,
+      "eval_samples_per_second": 11.444,
+      "eval_steps_per_second": 1.456,
+      "step": 1003
+    },
+    {
+      "epoch": 73.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.599768042564392,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.498,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 1017
+    },
+    {
+      "epoch": 74.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5934444665908813,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5664,
+      "eval_samples_per_second": 11.499,
+      "eval_steps_per_second": 1.463,
+      "step": 1031
+    },
+    {
+      "epoch": 76.0,
+      "eval_gen_len": 10.4091,
+      "eval_loss": 1.5867650508880615,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.579,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.462,
+      "step": 1045
+    },
+    {
+      "epoch": 76.95,
+      "eval_gen_len": 10.3,
+      "eval_loss": 1.5827070474624634,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.4875,
+      "eval_samples_per_second": 11.594,
+      "eval_steps_per_second": 1.476,
+      "step": 1058
+    },
+    {
+      "epoch": 77.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.5748482942581177,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4782,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1072
+    },
+    {
+      "epoch": 78.98,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 1.5662298202514648,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4778,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1086
+    },
+    {
+      "epoch": 80.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5585095882415771,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.4851,
+      "eval_samples_per_second": 11.597,
+      "eval_steps_per_second": 1.476,
+      "step": 1100
+    },
+    {
+      "epoch": 80.95,
+      "eval_gen_len": 10.1364,
+      "eval_loss": 1.5539778470993042,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6048,
+      "eval_samples_per_second": 11.453,
+      "eval_steps_per_second": 1.458,
+      "step": 1113
+    },
+    {
+      "epoch": 81.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.541092038154602,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4829,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 1127
+    },
+    {
+      "epoch": 82.98,
+      "eval_gen_len": 9.6091,
+      "eval_loss": 1.5330486297607422,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5558,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 1141
+    },
+    {
+      "epoch": 84.0,
+      "eval_gen_len": 9.0818,
+      "eval_loss": 1.5241070985794067,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6145,
+      "eval_samples_per_second": 11.441,
+      "eval_steps_per_second": 1.456,
+      "step": 1155
+    },
+    {
+      "epoch": 84.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.5192241668701172,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.4781,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1168
+    },
+    {
+      "epoch": 85.96,
+      "eval_gen_len": 9.5364,
+      "eval_loss": 1.5117179155349731,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5291,
+      "eval_samples_per_second": 11.544,
+      "eval_steps_per_second": 1.469,
+      "step": 1182
+    },
+    {
+      "epoch": 86.98,
+      "eval_gen_len": 9.4545,
+      "eval_loss": 1.4990766048431396,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6213,
+      "eval_samples_per_second": 11.433,
+      "eval_steps_per_second": 1.455,
+      "step": 1196
+    },
+    {
+      "epoch": 88.0,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 1.4878661632537842,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4886,
+      "eval_samples_per_second": 11.593,
+      "eval_steps_per_second": 1.475,
+      "step": 1210
+    },
+    {
+      "epoch": 88.95,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.479432463645935,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1223
+    },
+    {
+      "epoch": 89.96,
+      "eval_gen_len": 9.3909,
+      "eval_loss": 1.471197247505188,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 1237
+    },
+    {
+      "epoch": 90.98,
+      "eval_gen_len": 9.5,
+      "eval_loss": 1.4649511575698853,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5947,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 1251
+    },
+    {
+      "epoch": 92.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.4548052549362183,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0017,
+      "eval_runtime": 9.6868,
+      "eval_samples_per_second": 11.356,
+      "eval_steps_per_second": 1.445,
+      "step": 1265
+    },
+    {
+      "epoch": 92.95,
+      "eval_gen_len": 9.3727,
+      "eval_loss": 1.444838285446167,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 1278
+    },
+    {
+      "epoch": 93.96,
+      "eval_gen_len": 9.6,
+      "eval_loss": 1.4365838766098022,
+      "eval_rouge1": 0.0014,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0014,
+      "eval_rougeLsum": 0.0015,
+      "eval_runtime": 9.5507,
+      "eval_samples_per_second": 11.517,
+      "eval_steps_per_second": 1.466,
+      "step": 1292
+    },
+    {
+      "epoch": 94.98,
+      "eval_gen_len": 9.3364,
+      "eval_loss": 1.4285393953323364,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6323,
+      "eval_samples_per_second": 11.42,
+      "eval_steps_per_second": 1.453,
+      "step": 1306
+    },
+    {
+      "epoch": 96.0,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.4242411851882935,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 1320
+    },
+    {
+      "epoch": 96.95,
+      "eval_gen_len": 9.4,
+      "eval_loss": 1.4160754680633545,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1333
+    },
+    {
+      "epoch": 97.96,
+      "eval_gen_len": 9.4455,
+      "eval_loss": 1.4052343368530273,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6109,
+      "eval_samples_per_second": 11.445,
+      "eval_steps_per_second": 1.457,
+      "step": 1347
+    },
+    {
+      "epoch": 98.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.3928413391113281,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6591,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.449,
+      "step": 1361
+    },
+    {
+      "epoch": 100.0,
+      "eval_gen_len": 9.5182,
+      "eval_loss": 1.3840864896774292,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0011,
+      "eval_rougeLsum": 0.0011,
+      "eval_runtime": 9.6661,
+      "eval_samples_per_second": 11.38,
+      "eval_steps_per_second": 1.448,
+      "step": 1375
+    },
+    {
+      "epoch": 100.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.381872296333313,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0001,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6513,
+      "eval_samples_per_second": 11.397,
+      "eval_steps_per_second": 1.451,
+      "step": 1388
+    },
+    {
+      "epoch": 101.96,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.37588632106781,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.5607,
+      "eval_samples_per_second": 11.505,
+      "eval_steps_per_second": 1.464,
+      "step": 1402
+    },
+    {
+      "epoch": 102.98,
+      "eval_gen_len": 9.2636,
+      "eval_loss": 1.3675447702407837,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 1416
+    },
+    {
+      "epoch": 104.0,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 1.358955979347229,
+      "eval_rouge1": 0.0012,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0012,
+      "eval_rougeLsum": 0.0012,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1430
+    },
+    {
+      "epoch": 104.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.3501193523406982,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6684,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 1443
+    },
+    {
+      "epoch": 105.96,
+      "eval_gen_len": 9.1636,
+      "eval_loss": 1.344258189201355,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 1457
+    },
+    {
+      "epoch": 106.98,
+      "eval_gen_len": 9.8,
+      "eval_loss": 1.3355817794799805,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5263,
+      "eval_samples_per_second": 11.547,
+      "eval_steps_per_second": 1.47,
+      "step": 1471
+    },
+    {
+      "epoch": 108.0,
+      "eval_gen_len": 9.9182,
+      "eval_loss": 1.3305474519729614,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.6315,
+      "eval_samples_per_second": 11.421,
+      "eval_steps_per_second": 1.454,
+      "step": 1485
+    },
+    {
+      "epoch": 108.95,
+      "eval_gen_len": 10.1636,
+      "eval_loss": 1.3212946653366089,
+      "eval_rouge1": 0.0028,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0025,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.5797,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 1498
+    },
+    {
+      "epoch": 109.09,
+      "grad_norm": 5.480063438415527,
+      "learning_rate": 9.784615384615387e-06,
+      "loss": 1.7753,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2925,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 225,
+  "save_steps": 500,
+  "total_flos": 5.805822083648717e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa417b6b216c589bddc528e9d4e9c81b5edc8c24a516e2f555101dee203aa64c
+size 5048

checkpoint-2000/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: yhavinga/t5-base-dutch
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

checkpoint-2000/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "yhavinga/t5-base-dutch",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 24,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee915d6d204660e004fd7a9f28d33cce203d7ad18bfa204ef9dbcc38aabc1d3
+size 1789320

checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1e4917c51819247361479505c46b4572feb2f0fc883a49511abe98fa03fa4f
+size 3624250

checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b1466c7c91f7bcaf102e26c60827c90af98d7baac57b245a3924a6fe56521f2
+size 14244

checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0e9ea7b9fbc6f0ef7ba6aebcf0a443954f196d1052b2cb2ab55a09c068ebd39
+size 1064

checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2000/tokenizer_config.json

@@ -0,0 +1,937 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32100": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32101": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32102": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-2000/trainer_state.json

@@ -0,0 +1,1934 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 145.45454545454547,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "eval_gen_len": 13.1091,
+      "eval_loss": 21.40757179260254,
+      "eval_rouge1": 0.0745,
+      "eval_rouge2": 0.0159,
+      "eval_rougeL": 0.0584,
+      "eval_rougeLsum": 0.0582,
+      "eval_runtime": 11.5492,
+      "eval_samples_per_second": 9.524,
+      "eval_steps_per_second": 1.212,
+      "step": 13
+    },
+    {
+      "epoch": 1.96,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.254241943359375,
+      "eval_rouge1": 0.0726,
+      "eval_rouge2": 0.0153,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5424,
+      "eval_samples_per_second": 11.528,
+      "eval_steps_per_second": 1.467,
+      "step": 27
+    },
+    {
+      "epoch": 2.98,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.031164169311523,
+      "eval_rouge1": 0.0724,
+      "eval_rouge2": 0.0176,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5313,
+      "eval_samples_per_second": 11.541,
+      "eval_steps_per_second": 1.469,
+      "step": 41
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 12.6727,
+      "eval_loss": 20.743330001831055,
+      "eval_rouge1": 0.0722,
+      "eval_rouge2": 0.0175,
+      "eval_rougeL": 0.055,
+      "eval_rougeLsum": 0.0551,
+      "eval_runtime": 9.5638,
+      "eval_samples_per_second": 11.502,
+      "eval_steps_per_second": 1.464,
+      "step": 55
+    },
+    {
+      "epoch": 4.95,
+      "eval_gen_len": 12.5273,
+      "eval_loss": 20.430522918701172,
+      "eval_rouge1": 0.0708,
+      "eval_rouge2": 0.0177,
+      "eval_rougeL": 0.0545,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.583,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 68
+    },
+    {
+      "epoch": 5.96,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 20.10591697692871,
+      "eval_rouge1": 0.0725,
+      "eval_rouge2": 0.0185,
+      "eval_rougeL": 0.0559,
+      "eval_rougeLsum": 0.0559,
+      "eval_runtime": 9.5892,
+      "eval_samples_per_second": 11.471,
+      "eval_steps_per_second": 1.46,
+      "step": 82
+    },
+    {
+      "epoch": 6.98,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 19.850391387939453,
+      "eval_rouge1": 0.0727,
+      "eval_rouge2": 0.0169,
+      "eval_rougeL": 0.0551,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.6928,
+      "eval_samples_per_second": 11.349,
+      "eval_steps_per_second": 1.444,
+      "step": 96
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.628494262695312,
+      "eval_rouge1": 0.0816,
+      "eval_rouge2": 0.0228,
+      "eval_rougeL": 0.062,
+      "eval_rougeLsum": 0.0622,
+      "eval_runtime": 9.7244,
+      "eval_samples_per_second": 11.312,
+      "eval_steps_per_second": 1.44,
+      "step": 110
+    },
+    {
+      "epoch": 8.95,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.41258430480957,
+      "eval_rouge1": 0.0811,
+      "eval_rouge2": 0.0214,
+      "eval_rougeL": 0.0613,
+      "eval_rougeLsum": 0.0614,
+      "eval_runtime": 9.5996,
+      "eval_samples_per_second": 11.459,
+      "eval_steps_per_second": 1.458,
+      "step": 123
+    },
+    {
+      "epoch": 9.96,
+      "eval_gen_len": 13.5182,
+      "eval_loss": 19.160032272338867,
+      "eval_rouge1": 0.0818,
+      "eval_rouge2": 0.0208,
+      "eval_rougeL": 0.0632,
+      "eval_rougeLsum": 0.0633,
+      "eval_runtime": 9.5959,
+      "eval_samples_per_second": 11.463,
+      "eval_steps_per_second": 1.459,
+      "step": 137
+    },
+    {
+      "epoch": 10.98,
+      "eval_gen_len": 13.8909,
+      "eval_loss": 18.8905086517334,
+      "eval_rouge1": 0.09,
+      "eval_rouge2": 0.024,
+      "eval_rougeL": 0.0698,
+      "eval_rougeLsum": 0.0696,
+      "eval_runtime": 9.6532,
+      "eval_samples_per_second": 11.395,
+      "eval_steps_per_second": 1.45,
+      "step": 151
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 14.1818,
+      "eval_loss": 18.593591690063477,
+      "eval_rouge1": 0.094,
+      "eval_rouge2": 0.0324,
+      "eval_rougeL": 0.0735,
+      "eval_rougeLsum": 0.0732,
+      "eval_runtime": 9.6893,
+      "eval_samples_per_second": 11.353,
+      "eval_steps_per_second": 1.445,
+      "step": 165
+    },
+    {
+      "epoch": 12.95,
+      "eval_gen_len": 14.4364,
+      "eval_loss": 18.286243438720703,
+      "eval_rouge1": 0.0928,
+      "eval_rouge2": 0.0329,
+      "eval_rougeL": 0.0746,
+      "eval_rougeLsum": 0.0749,
+      "eval_runtime": 9.7163,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.441,
+      "step": 178
+    },
+    {
+      "epoch": 13.96,
+      "eval_gen_len": 15.0727,
+      "eval_loss": 17.896913528442383,
+      "eval_rouge1": 0.096,
+      "eval_rouge2": 0.0328,
+      "eval_rougeL": 0.0788,
+      "eval_rougeLsum": 0.0792,
+      "eval_runtime": 9.6929,
+      "eval_samples_per_second": 11.348,
+      "eval_steps_per_second": 1.444,
+      "step": 192
+    },
+    {
+      "epoch": 14.98,
+      "eval_gen_len": 15.7364,
+      "eval_loss": 17.442358016967773,
+      "eval_rouge1": 0.1015,
+      "eval_rouge2": 0.0334,
+      "eval_rougeL": 0.0816,
+      "eval_rougeLsum": 0.0818,
+      "eval_runtime": 9.6767,
+      "eval_samples_per_second": 11.368,
+      "eval_steps_per_second": 1.447,
+      "step": 206
+    },
+    {
+      "epoch": 16.0,
+      "eval_gen_len": 16.2364,
+      "eval_loss": 16.91552734375,
+      "eval_rouge1": 0.1001,
+      "eval_rouge2": 0.0337,
+      "eval_rougeL": 0.0811,
+      "eval_rougeLsum": 0.0814,
+      "eval_runtime": 9.5645,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 220
+    },
+    {
+      "epoch": 16.95,
+      "eval_gen_len": 16.6818,
+      "eval_loss": 16.372838973999023,
+      "eval_rouge1": 0.102,
+      "eval_rouge2": 0.0336,
+      "eval_rougeL": 0.081,
+      "eval_rougeLsum": 0.0809,
+      "eval_runtime": 9.7488,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 1.436,
+      "step": 233
+    },
+    {
+      "epoch": 17.96,
+      "eval_gen_len": 16.5364,
+      "eval_loss": 15.727865219116211,
+      "eval_rouge1": 0.0901,
+      "eval_rouge2": 0.0301,
+      "eval_rougeL": 0.0739,
+      "eval_rougeLsum": 0.0741,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 247
+    },
+    {
+      "epoch": 18.98,
+      "eval_gen_len": 16.9818,
+      "eval_loss": 14.980103492736816,
+      "eval_rouge1": 0.0828,
+      "eval_rouge2": 0.0258,
+      "eval_rougeL": 0.0673,
+      "eval_rougeLsum": 0.0671,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 261
+    },
+    {
+      "epoch": 20.0,
+      "eval_gen_len": 16.4727,
+      "eval_loss": 14.11096477508545,
+      "eval_rouge1": 0.0687,
+      "eval_rouge2": 0.0146,
+      "eval_rougeL": 0.0549,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.556,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 275
+    },
+    {
+      "epoch": 20.95,
+      "eval_gen_len": 14.2364,
+      "eval_loss": 13.337847709655762,
+      "eval_rouge1": 0.051,
+      "eval_rouge2": 0.0102,
+      "eval_rougeL": 0.0418,
+      "eval_rougeLsum": 0.0414,
+      "eval_runtime": 9.7157,
+      "eval_samples_per_second": 11.322,
+      "eval_steps_per_second": 1.441,
+      "step": 288
+    },
+    {
+      "epoch": 21.96,
+      "eval_gen_len": 12.3818,
+      "eval_loss": 12.585112571716309,
+      "eval_rouge1": 0.0377,
+      "eval_rouge2": 0.007,
+      "eval_rougeL": 0.0317,
+      "eval_rougeLsum": 0.0317,
+      "eval_runtime": 9.5457,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 302
+    },
+    {
+      "epoch": 22.98,
+      "eval_gen_len": 12.0455,
+      "eval_loss": 11.860977172851562,
+      "eval_rouge1": 0.023,
+      "eval_rouge2": 0.0048,
+      "eval_rougeL": 0.0204,
+      "eval_rougeLsum": 0.0204,
+      "eval_runtime": 9.5524,
+      "eval_samples_per_second": 11.515,
+      "eval_steps_per_second": 1.466,
+      "step": 316
+    },
+    {
+      "epoch": 24.0,
+      "eval_gen_len": 10.8545,
+      "eval_loss": 11.155168533325195,
+      "eval_rouge1": 0.012,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0108,
+      "eval_rougeLsum": 0.0108,
+      "eval_runtime": 9.5834,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 330
+    },
+    {
+      "epoch": 24.95,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 10.512735366821289,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0035,
+      "eval_rougeLsum": 0.0036,
+      "eval_runtime": 9.613,
+      "eval_samples_per_second": 11.443,
+      "eval_steps_per_second": 1.456,
+      "step": 343
+    },
+    {
+      "epoch": 25.96,
+      "eval_gen_len": 11.6,
+      "eval_loss": 9.83348560333252,
+      "eval_rouge1": 0.0039,
+      "eval_rouge2": 0.0002,
+      "eval_rougeL": 0.0038,
+      "eval_rougeLsum": 0.0039,
+      "eval_runtime": 9.5253,
+      "eval_samples_per_second": 11.548,
+      "eval_steps_per_second": 1.47,
+      "step": 357
+    },
+    {
+      "epoch": 26.98,
+      "eval_gen_len": 13.0455,
+      "eval_loss": 9.216172218322754,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5441,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 371
+    },
+    {
+      "epoch": 28.0,
+      "eval_gen_len": 14.6818,
+      "eval_loss": 8.572382926940918,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6018,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 385
+    },
+    {
+      "epoch": 28.95,
+      "eval_gen_len": 15.2727,
+      "eval_loss": 8.037731170654297,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0009,
+      "eval_rougeLsum": 0.0009,
+      "eval_runtime": 9.5646,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 398
+    },
+    {
+      "epoch": 29.96,
+      "eval_gen_len": 16.3909,
+      "eval_loss": 7.415070056915283,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5548,
+      "eval_samples_per_second": 11.513,
+      "eval_steps_per_second": 1.465,
+      "step": 412
+    },
+    {
+      "epoch": 30.98,
+      "eval_gen_len": 17.8364,
+      "eval_loss": 6.802865028381348,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5629,
+      "eval_samples_per_second": 11.503,
+      "eval_steps_per_second": 1.464,
+      "step": 426
+    },
+    {
+      "epoch": 32.0,
+      "eval_gen_len": 18.2818,
+      "eval_loss": 6.211207866668701,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 440
+    },
+    {
+      "epoch": 32.95,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.717328071594238,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.505,
+      "eval_samples_per_second": 11.573,
+      "eval_steps_per_second": 1.473,
+      "step": 453
+    },
+    {
+      "epoch": 33.96,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.17288064956665,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5443,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 467
+    },
+    {
+      "epoch": 34.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.669548034667969,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4845,
+      "eval_samples_per_second": 11.598,
+      "eval_steps_per_second": 1.476,
+      "step": 481
+    },
+    {
+      "epoch": 36.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.216309547424316,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5515,
+      "eval_samples_per_second": 11.516,
+      "eval_steps_per_second": 1.466,
+      "step": 495
+    },
+    {
+      "epoch": 36.36,
+      "grad_norm": 5.376431465148926,
+      "learning_rate": 1.660854700854701e-05,
+      "loss": 14.4939,
+      "step": 500
+    },
+    {
+      "epoch": 36.95,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.8450570106506348,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 508
+    },
+    {
+      "epoch": 37.96,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.507812261581421,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5902,
+      "eval_samples_per_second": 11.47,
+      "eval_steps_per_second": 1.46,
+      "step": 522
+    },
+    {
+      "epoch": 38.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.231505870819092,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5074,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 536
+    },
+    {
+      "epoch": 40.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.9967288970947266,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5195,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 550
+    },
+    {
+      "epoch": 40.95,
+      "eval_gen_len": 18.9545,
+      "eval_loss": 2.8089849948883057,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5224,
+      "eval_samples_per_second": 11.552,
+      "eval_steps_per_second": 1.47,
+      "step": 563
+    },
+    {
+      "epoch": 41.96,
+      "eval_gen_len": 18.3727,
+      "eval_loss": 2.6384663581848145,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5129,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 577
+    },
+    {
+      "epoch": 42.98,
+      "eval_gen_len": 16.7273,
+      "eval_loss": 2.492598295211792,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5174,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 591
+    },
+    {
+      "epoch": 44.0,
+      "eval_gen_len": 11.9636,
+      "eval_loss": 2.3677501678466797,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5796,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 605
+    },
+    {
+      "epoch": 44.95,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 2.2777955532073975,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6685,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 618
+    },
+    {
+      "epoch": 45.96,
+      "eval_gen_len": 7.9455,
+      "eval_loss": 2.198147773742676,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.585,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 632
+    },
+    {
+      "epoch": 46.98,
+      "eval_gen_len": 7.5909,
+      "eval_loss": 2.1306562423706055,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6008,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.458,
+      "step": 646
+    },
+    {
+      "epoch": 48.0,
+      "eval_gen_len": 7.4091,
+      "eval_loss": 2.0773117542266846,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.6506,
+      "eval_samples_per_second": 11.398,
+      "eval_steps_per_second": 1.451,
+      "step": 660
+    },
+    {
+      "epoch": 48.95,
+      "eval_gen_len": 7.2909,
+      "eval_loss": 2.036808729171753,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5097,
+      "eval_samples_per_second": 11.567,
+      "eval_steps_per_second": 1.472,
+      "step": 673
+    },
+    {
+      "epoch": 49.96,
+      "eval_gen_len": 6.8364,
+      "eval_loss": 1.9949748516082764,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6031,
+      "eval_samples_per_second": 11.455,
+      "eval_steps_per_second": 1.458,
+      "step": 687
+    },
+    {
+      "epoch": 50.98,
+      "eval_gen_len": 7.8273,
+      "eval_loss": 1.957520842552185,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 701
+    },
+    {
+      "epoch": 52.0,
+      "eval_gen_len": 7.5545,
+      "eval_loss": 1.9219788312911987,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5836,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 715
+    },
+    {
+      "epoch": 52.95,
+      "eval_gen_len": 7.5364,
+      "eval_loss": 1.8916202783584595,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 728
+    },
+    {
+      "epoch": 53.96,
+      "eval_gen_len": 7.1182,
+      "eval_loss": 1.8674402236938477,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5024,
+      "eval_samples_per_second": 11.576,
+      "eval_steps_per_second": 1.473,
+      "step": 742
+    },
+    {
+      "epoch": 54.98,
+      "eval_gen_len": 7.0364,
+      "eval_loss": 1.846158742904663,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 756
+    },
+    {
+      "epoch": 56.0,
+      "eval_gen_len": 7.0,
+      "eval_loss": 1.827086329460144,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.591,
+      "eval_samples_per_second": 11.469,
+      "eval_steps_per_second": 1.46,
+      "step": 770
+    },
+    {
+      "epoch": 56.95,
+      "eval_gen_len": 7.5455,
+      "eval_loss": 1.8088210821151733,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.572,
+      "eval_samples_per_second": 11.492,
+      "eval_steps_per_second": 1.463,
+      "step": 783
+    },
+    {
+      "epoch": 57.96,
+      "eval_gen_len": 7.9,
+      "eval_loss": 1.789602279663086,
+      "eval_rouge1": 0.0001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0001,
+      "eval_rougeLsum": 0.0001,
+      "eval_runtime": 9.5837,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 797
+    },
+    {
+      "epoch": 58.98,
+      "eval_gen_len": 8.2545,
+      "eval_loss": 1.7687013149261475,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6152,
+      "eval_samples_per_second": 11.44,
+      "eval_steps_per_second": 1.456,
+      "step": 811
+    },
+    {
+      "epoch": 60.0,
+      "eval_gen_len": 8.3636,
+      "eval_loss": 1.7496564388275146,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4902,
+      "eval_samples_per_second": 11.591,
+      "eval_steps_per_second": 1.475,
+      "step": 825
+    },
+    {
+      "epoch": 60.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.7332907915115356,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 838
+    },
+    {
+      "epoch": 61.96,
+      "eval_gen_len": 8.9,
+      "eval_loss": 1.7185932397842407,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4797,
+      "eval_samples_per_second": 11.604,
+      "eval_steps_per_second": 1.477,
+      "step": 852
+    },
+    {
+      "epoch": 62.98,
+      "eval_gen_len": 9.7545,
+      "eval_loss": 1.7047526836395264,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.618,
+      "eval_samples_per_second": 11.437,
+      "eval_steps_per_second": 1.456,
+      "step": 866
+    },
+    {
+      "epoch": 64.0,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 1.6921414136886597,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6264,
+      "eval_samples_per_second": 11.427,
+      "eval_steps_per_second": 1.454,
+      "step": 880
+    },
+    {
+      "epoch": 64.95,
+      "eval_gen_len": 9.6909,
+      "eval_loss": 1.6816327571868896,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5134,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 893
+    },
+    {
+      "epoch": 65.96,
+      "eval_gen_len": 8.9545,
+      "eval_loss": 1.6697723865509033,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5506,
+      "eval_samples_per_second": 11.518,
+      "eval_steps_per_second": 1.466,
+      "step": 907
+    },
+    {
+      "epoch": 66.98,
+      "eval_gen_len": 9.6818,
+      "eval_loss": 1.6568113565444946,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 921
+    },
+    {
+      "epoch": 68.0,
+      "eval_gen_len": 9.9455,
+      "eval_loss": 1.6469463109970093,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4825,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 935
+    },
+    {
+      "epoch": 68.95,
+      "eval_gen_len": 9.3545,
+      "eval_loss": 1.6408612728118896,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5212,
+      "eval_samples_per_second": 11.553,
+      "eval_steps_per_second": 1.47,
+      "step": 948
+    },
+    {
+      "epoch": 69.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.6316603422164917,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4986,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 962
+    },
+    {
+      "epoch": 70.98,
+      "eval_gen_len": 9.7818,
+      "eval_loss": 1.623169183731079,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5276,
+      "eval_samples_per_second": 11.545,
+      "eval_steps_per_second": 1.469,
+      "step": 976
+    },
+    {
+      "epoch": 72.0,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 1.6152759790420532,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5801,
+      "eval_samples_per_second": 11.482,
+      "eval_steps_per_second": 1.461,
+      "step": 990
+    },
+    {
+      "epoch": 72.73,
+      "grad_norm": 3.344996213912964,
+      "learning_rate": 1.3196581196581197e-05,
+      "loss": 2.6089,
+      "step": 1000
+    },
+    {
+      "epoch": 72.95,
+      "eval_gen_len": 9.1727,
+      "eval_loss": 1.6071548461914062,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.6124,
+      "eval_samples_per_second": 11.444,
+      "eval_steps_per_second": 1.456,
+      "step": 1003
+    },
+    {
+      "epoch": 73.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.599768042564392,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.498,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 1017
+    },
+    {
+      "epoch": 74.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5934444665908813,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5664,
+      "eval_samples_per_second": 11.499,
+      "eval_steps_per_second": 1.463,
+      "step": 1031
+    },
+    {
+      "epoch": 76.0,
+      "eval_gen_len": 10.4091,
+      "eval_loss": 1.5867650508880615,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.579,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.462,
+      "step": 1045
+    },
+    {
+      "epoch": 76.95,
+      "eval_gen_len": 10.3,
+      "eval_loss": 1.5827070474624634,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.4875,
+      "eval_samples_per_second": 11.594,
+      "eval_steps_per_second": 1.476,
+      "step": 1058
+    },
+    {
+      "epoch": 77.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.5748482942581177,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4782,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1072
+    },
+    {
+      "epoch": 78.98,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 1.5662298202514648,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4778,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1086
+    },
+    {
+      "epoch": 80.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5585095882415771,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.4851,
+      "eval_samples_per_second": 11.597,
+      "eval_steps_per_second": 1.476,
+      "step": 1100
+    },
+    {
+      "epoch": 80.95,
+      "eval_gen_len": 10.1364,
+      "eval_loss": 1.5539778470993042,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6048,
+      "eval_samples_per_second": 11.453,
+      "eval_steps_per_second": 1.458,
+      "step": 1113
+    },
+    {
+      "epoch": 81.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.541092038154602,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4829,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 1127
+    },
+    {
+      "epoch": 82.98,
+      "eval_gen_len": 9.6091,
+      "eval_loss": 1.5330486297607422,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5558,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 1141
+    },
+    {
+      "epoch": 84.0,
+      "eval_gen_len": 9.0818,
+      "eval_loss": 1.5241070985794067,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6145,
+      "eval_samples_per_second": 11.441,
+      "eval_steps_per_second": 1.456,
+      "step": 1155
+    },
+    {
+      "epoch": 84.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.5192241668701172,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.4781,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1168
+    },
+    {
+      "epoch": 85.96,
+      "eval_gen_len": 9.5364,
+      "eval_loss": 1.5117179155349731,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5291,
+      "eval_samples_per_second": 11.544,
+      "eval_steps_per_second": 1.469,
+      "step": 1182
+    },
+    {
+      "epoch": 86.98,
+      "eval_gen_len": 9.4545,
+      "eval_loss": 1.4990766048431396,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6213,
+      "eval_samples_per_second": 11.433,
+      "eval_steps_per_second": 1.455,
+      "step": 1196
+    },
+    {
+      "epoch": 88.0,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 1.4878661632537842,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4886,
+      "eval_samples_per_second": 11.593,
+      "eval_steps_per_second": 1.475,
+      "step": 1210
+    },
+    {
+      "epoch": 88.95,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.479432463645935,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1223
+    },
+    {
+      "epoch": 89.96,
+      "eval_gen_len": 9.3909,
+      "eval_loss": 1.471197247505188,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 1237
+    },
+    {
+      "epoch": 90.98,
+      "eval_gen_len": 9.5,
+      "eval_loss": 1.4649511575698853,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5947,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 1251
+    },
+    {
+      "epoch": 92.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.4548052549362183,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0017,
+      "eval_runtime": 9.6868,
+      "eval_samples_per_second": 11.356,
+      "eval_steps_per_second": 1.445,
+      "step": 1265
+    },
+    {
+      "epoch": 92.95,
+      "eval_gen_len": 9.3727,
+      "eval_loss": 1.444838285446167,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 1278
+    },
+    {
+      "epoch": 93.96,
+      "eval_gen_len": 9.6,
+      "eval_loss": 1.4365838766098022,
+      "eval_rouge1": 0.0014,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0014,
+      "eval_rougeLsum": 0.0015,
+      "eval_runtime": 9.5507,
+      "eval_samples_per_second": 11.517,
+      "eval_steps_per_second": 1.466,
+      "step": 1292
+    },
+    {
+      "epoch": 94.98,
+      "eval_gen_len": 9.3364,
+      "eval_loss": 1.4285393953323364,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6323,
+      "eval_samples_per_second": 11.42,
+      "eval_steps_per_second": 1.453,
+      "step": 1306
+    },
+    {
+      "epoch": 96.0,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.4242411851882935,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 1320
+    },
+    {
+      "epoch": 96.95,
+      "eval_gen_len": 9.4,
+      "eval_loss": 1.4160754680633545,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1333
+    },
+    {
+      "epoch": 97.96,
+      "eval_gen_len": 9.4455,
+      "eval_loss": 1.4052343368530273,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6109,
+      "eval_samples_per_second": 11.445,
+      "eval_steps_per_second": 1.457,
+      "step": 1347
+    },
+    {
+      "epoch": 98.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.3928413391113281,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6591,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.449,
+      "step": 1361
+    },
+    {
+      "epoch": 100.0,
+      "eval_gen_len": 9.5182,
+      "eval_loss": 1.3840864896774292,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0011,
+      "eval_rougeLsum": 0.0011,
+      "eval_runtime": 9.6661,
+      "eval_samples_per_second": 11.38,
+      "eval_steps_per_second": 1.448,
+      "step": 1375
+    },
+    {
+      "epoch": 100.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.381872296333313,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0001,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6513,
+      "eval_samples_per_second": 11.397,
+      "eval_steps_per_second": 1.451,
+      "step": 1388
+    },
+    {
+      "epoch": 101.96,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.37588632106781,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.5607,
+      "eval_samples_per_second": 11.505,
+      "eval_steps_per_second": 1.464,
+      "step": 1402
+    },
+    {
+      "epoch": 102.98,
+      "eval_gen_len": 9.2636,
+      "eval_loss": 1.3675447702407837,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 1416
+    },
+    {
+      "epoch": 104.0,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 1.358955979347229,
+      "eval_rouge1": 0.0012,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0012,
+      "eval_rougeLsum": 0.0012,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1430
+    },
+    {
+      "epoch": 104.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.3501193523406982,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6684,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 1443
+    },
+    {
+      "epoch": 105.96,
+      "eval_gen_len": 9.1636,
+      "eval_loss": 1.344258189201355,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 1457
+    },
+    {
+      "epoch": 106.98,
+      "eval_gen_len": 9.8,
+      "eval_loss": 1.3355817794799805,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5263,
+      "eval_samples_per_second": 11.547,
+      "eval_steps_per_second": 1.47,
+      "step": 1471
+    },
+    {
+      "epoch": 108.0,
+      "eval_gen_len": 9.9182,
+      "eval_loss": 1.3305474519729614,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.6315,
+      "eval_samples_per_second": 11.421,
+      "eval_steps_per_second": 1.454,
+      "step": 1485
+    },
+    {
+      "epoch": 108.95,
+      "eval_gen_len": 10.1636,
+      "eval_loss": 1.3212946653366089,
+      "eval_rouge1": 0.0028,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0025,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.5797,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 1498
+    },
+    {
+      "epoch": 109.09,
+      "grad_norm": 5.480063438415527,
+      "learning_rate": 9.784615384615387e-06,
+      "loss": 1.7753,
+      "step": 1500
+    },
+    {
+      "epoch": 109.96,
+      "eval_gen_len": 9.9091,
+      "eval_loss": 1.31065833568573,
+      "eval_rouge1": 0.0019,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0015,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.57,
+      "eval_samples_per_second": 11.494,
+      "eval_steps_per_second": 1.463,
+      "step": 1512
+    },
+    {
+      "epoch": 110.98,
+      "eval_gen_len": 10.2,
+      "eval_loss": 1.301637053489685,
+      "eval_rouge1": 0.0015,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0013,
+      "eval_runtime": 9.5009,
+      "eval_samples_per_second": 11.578,
+      "eval_steps_per_second": 1.474,
+      "step": 1526
+    },
+    {
+      "epoch": 112.0,
+      "eval_gen_len": 9.7091,
+      "eval_loss": 1.2922732830047607,
+      "eval_rouge1": 0.0014,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0014,
+      "eval_runtime": 9.5171,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 1540
+    },
+    {
+      "epoch": 112.95,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 1.2817051410675049,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.001,
+      "eval_rougeLsum": 0.001,
+      "eval_runtime": 9.5296,
+      "eval_samples_per_second": 11.543,
+      "eval_steps_per_second": 1.469,
+      "step": 1553
+    },
+    {
+      "epoch": 113.96,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 1.2726068496704102,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.001,
+      "eval_rougeLsum": 0.001,
+      "eval_runtime": 9.6467,
+      "eval_samples_per_second": 11.403,
+      "eval_steps_per_second": 1.451,
+      "step": 1567
+    },
+    {
+      "epoch": 114.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.2626111507415771,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 11.578,
+      "eval_steps_per_second": 1.474,
+      "step": 1581
+    },
+    {
+      "epoch": 116.0,
+      "eval_gen_len": 9.8,
+      "eval_loss": 1.2526050806045532,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0019,
+      "eval_rougeLsum": 0.0019,
+      "eval_runtime": 9.5945,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 1595
+    },
+    {
+      "epoch": 116.95,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.2438002824783325,
+      "eval_rouge1": 0.0012,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0012,
+      "eval_rougeLsum": 0.0012,
+      "eval_runtime": 9.582,
+      "eval_samples_per_second": 11.48,
+      "eval_steps_per_second": 1.461,
+      "step": 1608
+    },
+    {
+      "epoch": 117.96,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.235589861869812,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0013,
+      "eval_runtime": 9.5074,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 1622
+    },
+    {
+      "epoch": 118.98,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.2265100479125977,
+      "eval_rouge1": 0.0017,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0017,
+      "eval_rougeLsum": 0.0017,
+      "eval_runtime": 9.6164,
+      "eval_samples_per_second": 11.439,
+      "eval_steps_per_second": 1.456,
+      "step": 1636
+    },
+    {
+      "epoch": 120.0,
+      "eval_gen_len": 9.7182,
+      "eval_loss": 1.21653151512146,
+      "eval_rouge1": 0.0013,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0011,
+      "eval_rougeLsum": 0.0011,
+      "eval_runtime": 9.5387,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 1650
+    },
+    {
+      "epoch": 120.95,
+      "eval_gen_len": 9.7182,
+      "eval_loss": 1.208518624305725,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0014,
+      "eval_rougeLsum": 0.0015,
+      "eval_runtime": 9.6008,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.458,
+      "step": 1663
+    },
+    {
+      "epoch": 121.96,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 1.1974164247512817,
+      "eval_rouge1": 0.0024,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0022,
+      "eval_rougeLsum": 0.0022,
+      "eval_runtime": 9.5182,
+      "eval_samples_per_second": 11.557,
+      "eval_steps_per_second": 1.471,
+      "step": 1677
+    },
+    {
+      "epoch": 122.98,
+      "eval_gen_len": 9.3273,
+      "eval_loss": 1.188578486442566,
+      "eval_rouge1": 0.0013,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0009,
+      "eval_runtime": 9.5875,
+      "eval_samples_per_second": 11.473,
+      "eval_steps_per_second": 1.46,
+      "step": 1691
+    },
+    {
+      "epoch": 124.0,
+      "eval_gen_len": 9.3727,
+      "eval_loss": 1.1796928644180298,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0018,
+      "eval_rougeLsum": 0.0018,
+      "eval_runtime": 9.5197,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1705
+    },
+    {
+      "epoch": 124.95,
+      "eval_gen_len": 9.4091,
+      "eval_loss": 1.1718236207962036,
+      "eval_rouge1": 0.0021,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0018,
+      "eval_rougeLsum": 0.0018,
+      "eval_runtime": 9.5197,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1718
+    },
+    {
+      "epoch": 125.96,
+      "eval_gen_len": 9.3364,
+      "eval_loss": 1.1624401807785034,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.5347,
+      "eval_samples_per_second": 11.537,
+      "eval_steps_per_second": 1.468,
+      "step": 1732
+    },
+    {
+      "epoch": 126.98,
+      "eval_gen_len": 9.6364,
+      "eval_loss": 1.1539288759231567,
+      "eval_rouge1": 0.0041,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0032,
+      "eval_rougeLsum": 0.0032,
+      "eval_runtime": 9.4835,
+      "eval_samples_per_second": 11.599,
+      "eval_steps_per_second": 1.476,
+      "step": 1746
+    },
+    {
+      "epoch": 128.0,
+      "eval_gen_len": 9.5364,
+      "eval_loss": 1.1447480916976929,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0017,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5263,
+      "eval_samples_per_second": 11.547,
+      "eval_steps_per_second": 1.47,
+      "step": 1760
+    },
+    {
+      "epoch": 128.95,
+      "eval_gen_len": 9.4545,
+      "eval_loss": 1.1359179019927979,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0021,
+      "eval_rougeLsum": 0.0021,
+      "eval_runtime": 9.5577,
+      "eval_samples_per_second": 11.509,
+      "eval_steps_per_second": 1.465,
+      "step": 1773
+    },
+    {
+      "epoch": 129.96,
+      "eval_gen_len": 9.3636,
+      "eval_loss": 1.1250239610671997,
+      "eval_rouge1": 0.0029,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0026,
+      "eval_rougeLsum": 0.0025,
+      "eval_runtime": 9.5118,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 1.472,
+      "step": 1787
+    },
+    {
+      "epoch": 130.98,
+      "eval_gen_len": 9.4364,
+      "eval_loss": 1.1156790256500244,
+      "eval_rouge1": 0.0034,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0031,
+      "eval_rougeLsum": 0.003,
+      "eval_runtime": 9.4869,
+      "eval_samples_per_second": 11.595,
+      "eval_steps_per_second": 1.476,
+      "step": 1801
+    },
+    {
+      "epoch": 132.0,
+      "eval_gen_len": 9.5182,
+      "eval_loss": 1.1065722703933716,
+      "eval_rouge1": 0.0029,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0027,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.6053,
+      "eval_samples_per_second": 11.452,
+      "eval_steps_per_second": 1.458,
+      "step": 1815
+    },
+    {
+      "epoch": 132.95,
+      "eval_gen_len": 9.6636,
+      "eval_loss": 1.0981847047805786,
+      "eval_rouge1": 0.0032,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0034,
+      "eval_rougeLsum": 0.0032,
+      "eval_runtime": 9.6558,
+      "eval_samples_per_second": 11.392,
+      "eval_steps_per_second": 1.45,
+      "step": 1828
+    },
+    {
+      "epoch": 133.96,
+      "eval_gen_len": 9.7273,
+      "eval_loss": 1.090613603591919,
+      "eval_rouge1": 0.0032,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0031,
+      "eval_rougeLsum": 0.0029,
+      "eval_runtime": 9.6549,
+      "eval_samples_per_second": 11.393,
+      "eval_steps_per_second": 1.45,
+      "step": 1842
+    },
+    {
+      "epoch": 134.98,
+      "eval_gen_len": 10.0818,
+      "eval_loss": 1.0842803716659546,
+      "eval_rouge1": 0.0061,
+      "eval_rouge2": 0.0008,
+      "eval_rougeL": 0.0052,
+      "eval_rougeLsum": 0.0052,
+      "eval_runtime": 9.4978,
+      "eval_samples_per_second": 11.582,
+      "eval_steps_per_second": 1.474,
+      "step": 1856
+    },
+    {
+      "epoch": 136.0,
+      "eval_gen_len": 9.5818,
+      "eval_loss": 1.075701117515564,
+      "eval_rouge1": 0.0046,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0042,
+      "eval_rougeLsum": 0.0042,
+      "eval_runtime": 9.6101,
+      "eval_samples_per_second": 11.446,
+      "eval_steps_per_second": 1.457,
+      "step": 1870
+    },
+    {
+      "epoch": 136.95,
+      "eval_gen_len": 9.8273,
+      "eval_loss": 1.0663608312606812,
+      "eval_rouge1": 0.0048,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0043,
+      "eval_rougeLsum": 0.0043,
+      "eval_runtime": 9.6501,
+      "eval_samples_per_second": 11.399,
+      "eval_steps_per_second": 1.451,
+      "step": 1883
+    },
+    {
+      "epoch": 137.96,
+      "eval_gen_len": 9.8545,
+      "eval_loss": 1.0555903911590576,
+      "eval_rouge1": 0.0055,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0046,
+      "eval_rougeLsum": 0.0045,
+      "eval_runtime": 9.5822,
+      "eval_samples_per_second": 11.48,
+      "eval_steps_per_second": 1.461,
+      "step": 1897
+    },
+    {
+      "epoch": 138.98,
+      "eval_gen_len": 9.9182,
+      "eval_loss": 1.0459803342819214,
+      "eval_rouge1": 0.0067,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0063,
+      "eval_rougeLsum": 0.0062,
+      "eval_runtime": 9.659,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.449,
+      "step": 1911
+    },
+    {
+      "epoch": 140.0,
+      "eval_gen_len": 10.1636,
+      "eval_loss": 1.0374290943145752,
+      "eval_rouge1": 0.0067,
+      "eval_rouge2": 0.0017,
+      "eval_rougeL": 0.0062,
+      "eval_rougeLsum": 0.0061,
+      "eval_runtime": 9.5201,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1925
+    },
+    {
+      "epoch": 140.95,
+      "eval_gen_len": 9.8909,
+      "eval_loss": 1.0285921096801758,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0034,
+      "eval_rougeLsum": 0.0034,
+      "eval_runtime": 9.5989,
+      "eval_samples_per_second": 11.46,
+      "eval_steps_per_second": 1.458,
+      "step": 1938
+    },
+    {
+      "epoch": 141.96,
+      "eval_gen_len": 9.6455,
+      "eval_loss": 1.0195242166519165,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0027,
+      "eval_runtime": 9.5173,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 1952
+    },
+    {
+      "epoch": 142.98,
+      "eval_gen_len": 9.8182,
+      "eval_loss": 1.0105475187301636,
+      "eval_rouge1": 0.0031,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5853,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 1966
+    },
+    {
+      "epoch": 144.0,
+      "eval_gen_len": 9.5091,
+      "eval_loss": 1.001856803894043,
+      "eval_rouge1": 0.0025,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0022,
+      "eval_rougeLsum": 0.002,
+      "eval_runtime": 9.5828,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 1980
+    },
+    {
+      "epoch": 144.95,
+      "eval_gen_len": 9.6909,
+      "eval_loss": 0.9937859773635864,
+      "eval_rouge1": 0.0023,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.5054,
+      "eval_samples_per_second": 11.572,
+      "eval_steps_per_second": 1.473,
+      "step": 1993
+    },
+    {
+      "epoch": 145.45,
+      "grad_norm": 3.3901820182800293,
+      "learning_rate": 6.365811965811967e-06,
+      "loss": 1.4532,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2925,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 225,
+  "save_steps": 500,
+  "total_flos": 7.741258862690304e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa417b6b216c589bddc528e9d4e9c81b5edc8c24a516e2f555101dee203aa64c
+size 5048

checkpoint-2500/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: yhavinga/t5-base-dutch
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.9.0

checkpoint-2500/adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "yhavinga/t5-base-dutch",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 24,
+  "lora_dropout": 0.01,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q",
+    "v"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-2500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afdf56cee8556622639772753b0439c7f9b6762f693c51f073ec6f4865494f0
+size 1789320

checkpoint-2500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4563208ae25d83e2ba70c03b9c95df595d0b3bc82fd005f5d882bea8634848c3
+size 3624250

checkpoint-2500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b13cad1d9bd34840742bc502791abb69f2482aa458d971a254c103aca164b5
+size 14244

checkpoint-2500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be5f7e00cbcb5659de4023ee4b7f89b34dd691f5fb6777206282a4bebe6dd52e
+size 1064

checkpoint-2500/special_tokens_map.json

@@ -0,0 +1,125 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-2500/tokenizer_config.json

@@ -0,0 +1,937 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32100": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32101": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32102": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-2500/trainer_state.json

@@ -0,0 +1,2409 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 181.8181818181818,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.95,
+      "eval_gen_len": 13.1091,
+      "eval_loss": 21.40757179260254,
+      "eval_rouge1": 0.0745,
+      "eval_rouge2": 0.0159,
+      "eval_rougeL": 0.0584,
+      "eval_rougeLsum": 0.0582,
+      "eval_runtime": 11.5492,
+      "eval_samples_per_second": 9.524,
+      "eval_steps_per_second": 1.212,
+      "step": 13
+    },
+    {
+      "epoch": 1.96,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.254241943359375,
+      "eval_rouge1": 0.0726,
+      "eval_rouge2": 0.0153,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5424,
+      "eval_samples_per_second": 11.528,
+      "eval_steps_per_second": 1.467,
+      "step": 27
+    },
+    {
+      "epoch": 2.98,
+      "eval_gen_len": 12.9636,
+      "eval_loss": 21.031164169311523,
+      "eval_rouge1": 0.0724,
+      "eval_rouge2": 0.0176,
+      "eval_rougeL": 0.0568,
+      "eval_rougeLsum": 0.0569,
+      "eval_runtime": 9.5313,
+      "eval_samples_per_second": 11.541,
+      "eval_steps_per_second": 1.469,
+      "step": 41
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 12.6727,
+      "eval_loss": 20.743330001831055,
+      "eval_rouge1": 0.0722,
+      "eval_rouge2": 0.0175,
+      "eval_rougeL": 0.055,
+      "eval_rougeLsum": 0.0551,
+      "eval_runtime": 9.5638,
+      "eval_samples_per_second": 11.502,
+      "eval_steps_per_second": 1.464,
+      "step": 55
+    },
+    {
+      "epoch": 4.95,
+      "eval_gen_len": 12.5273,
+      "eval_loss": 20.430522918701172,
+      "eval_rouge1": 0.0708,
+      "eval_rouge2": 0.0177,
+      "eval_rougeL": 0.0545,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.583,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 68
+    },
+    {
+      "epoch": 5.96,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 20.10591697692871,
+      "eval_rouge1": 0.0725,
+      "eval_rouge2": 0.0185,
+      "eval_rougeL": 0.0559,
+      "eval_rougeLsum": 0.0559,
+      "eval_runtime": 9.5892,
+      "eval_samples_per_second": 11.471,
+      "eval_steps_per_second": 1.46,
+      "step": 82
+    },
+    {
+      "epoch": 6.98,
+      "eval_gen_len": 12.6091,
+      "eval_loss": 19.850391387939453,
+      "eval_rouge1": 0.0727,
+      "eval_rouge2": 0.0169,
+      "eval_rougeL": 0.0551,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.6928,
+      "eval_samples_per_second": 11.349,
+      "eval_steps_per_second": 1.444,
+      "step": 96
+    },
+    {
+      "epoch": 8.0,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.628494262695312,
+      "eval_rouge1": 0.0816,
+      "eval_rouge2": 0.0228,
+      "eval_rougeL": 0.062,
+      "eval_rougeLsum": 0.0622,
+      "eval_runtime": 9.7244,
+      "eval_samples_per_second": 11.312,
+      "eval_steps_per_second": 1.44,
+      "step": 110
+    },
+    {
+      "epoch": 8.95,
+      "eval_gen_len": 13.2909,
+      "eval_loss": 19.41258430480957,
+      "eval_rouge1": 0.0811,
+      "eval_rouge2": 0.0214,
+      "eval_rougeL": 0.0613,
+      "eval_rougeLsum": 0.0614,
+      "eval_runtime": 9.5996,
+      "eval_samples_per_second": 11.459,
+      "eval_steps_per_second": 1.458,
+      "step": 123
+    },
+    {
+      "epoch": 9.96,
+      "eval_gen_len": 13.5182,
+      "eval_loss": 19.160032272338867,
+      "eval_rouge1": 0.0818,
+      "eval_rouge2": 0.0208,
+      "eval_rougeL": 0.0632,
+      "eval_rougeLsum": 0.0633,
+      "eval_runtime": 9.5959,
+      "eval_samples_per_second": 11.463,
+      "eval_steps_per_second": 1.459,
+      "step": 137
+    },
+    {
+      "epoch": 10.98,
+      "eval_gen_len": 13.8909,
+      "eval_loss": 18.8905086517334,
+      "eval_rouge1": 0.09,
+      "eval_rouge2": 0.024,
+      "eval_rougeL": 0.0698,
+      "eval_rougeLsum": 0.0696,
+      "eval_runtime": 9.6532,
+      "eval_samples_per_second": 11.395,
+      "eval_steps_per_second": 1.45,
+      "step": 151
+    },
+    {
+      "epoch": 12.0,
+      "eval_gen_len": 14.1818,
+      "eval_loss": 18.593591690063477,
+      "eval_rouge1": 0.094,
+      "eval_rouge2": 0.0324,
+      "eval_rougeL": 0.0735,
+      "eval_rougeLsum": 0.0732,
+      "eval_runtime": 9.6893,
+      "eval_samples_per_second": 11.353,
+      "eval_steps_per_second": 1.445,
+      "step": 165
+    },
+    {
+      "epoch": 12.95,
+      "eval_gen_len": 14.4364,
+      "eval_loss": 18.286243438720703,
+      "eval_rouge1": 0.0928,
+      "eval_rouge2": 0.0329,
+      "eval_rougeL": 0.0746,
+      "eval_rougeLsum": 0.0749,
+      "eval_runtime": 9.7163,
+      "eval_samples_per_second": 11.321,
+      "eval_steps_per_second": 1.441,
+      "step": 178
+    },
+    {
+      "epoch": 13.96,
+      "eval_gen_len": 15.0727,
+      "eval_loss": 17.896913528442383,
+      "eval_rouge1": 0.096,
+      "eval_rouge2": 0.0328,
+      "eval_rougeL": 0.0788,
+      "eval_rougeLsum": 0.0792,
+      "eval_runtime": 9.6929,
+      "eval_samples_per_second": 11.348,
+      "eval_steps_per_second": 1.444,
+      "step": 192
+    },
+    {
+      "epoch": 14.98,
+      "eval_gen_len": 15.7364,
+      "eval_loss": 17.442358016967773,
+      "eval_rouge1": 0.1015,
+      "eval_rouge2": 0.0334,
+      "eval_rougeL": 0.0816,
+      "eval_rougeLsum": 0.0818,
+      "eval_runtime": 9.6767,
+      "eval_samples_per_second": 11.368,
+      "eval_steps_per_second": 1.447,
+      "step": 206
+    },
+    {
+      "epoch": 16.0,
+      "eval_gen_len": 16.2364,
+      "eval_loss": 16.91552734375,
+      "eval_rouge1": 0.1001,
+      "eval_rouge2": 0.0337,
+      "eval_rougeL": 0.0811,
+      "eval_rougeLsum": 0.0814,
+      "eval_runtime": 9.5645,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 220
+    },
+    {
+      "epoch": 16.95,
+      "eval_gen_len": 16.6818,
+      "eval_loss": 16.372838973999023,
+      "eval_rouge1": 0.102,
+      "eval_rouge2": 0.0336,
+      "eval_rougeL": 0.081,
+      "eval_rougeLsum": 0.0809,
+      "eval_runtime": 9.7488,
+      "eval_samples_per_second": 11.283,
+      "eval_steps_per_second": 1.436,
+      "step": 233
+    },
+    {
+      "epoch": 17.96,
+      "eval_gen_len": 16.5364,
+      "eval_loss": 15.727865219116211,
+      "eval_rouge1": 0.0901,
+      "eval_rouge2": 0.0301,
+      "eval_rougeL": 0.0739,
+      "eval_rougeLsum": 0.0741,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 247
+    },
+    {
+      "epoch": 18.98,
+      "eval_gen_len": 16.9818,
+      "eval_loss": 14.980103492736816,
+      "eval_rouge1": 0.0828,
+      "eval_rouge2": 0.0258,
+      "eval_rougeL": 0.0673,
+      "eval_rougeLsum": 0.0671,
+      "eval_runtime": 9.6417,
+      "eval_samples_per_second": 11.409,
+      "eval_steps_per_second": 1.452,
+      "step": 261
+    },
+    {
+      "epoch": 20.0,
+      "eval_gen_len": 16.4727,
+      "eval_loss": 14.11096477508545,
+      "eval_rouge1": 0.0687,
+      "eval_rouge2": 0.0146,
+      "eval_rougeL": 0.0549,
+      "eval_rougeLsum": 0.0547,
+      "eval_runtime": 9.556,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 275
+    },
+    {
+      "epoch": 20.95,
+      "eval_gen_len": 14.2364,
+      "eval_loss": 13.337847709655762,
+      "eval_rouge1": 0.051,
+      "eval_rouge2": 0.0102,
+      "eval_rougeL": 0.0418,
+      "eval_rougeLsum": 0.0414,
+      "eval_runtime": 9.7157,
+      "eval_samples_per_second": 11.322,
+      "eval_steps_per_second": 1.441,
+      "step": 288
+    },
+    {
+      "epoch": 21.96,
+      "eval_gen_len": 12.3818,
+      "eval_loss": 12.585112571716309,
+      "eval_rouge1": 0.0377,
+      "eval_rouge2": 0.007,
+      "eval_rougeL": 0.0317,
+      "eval_rougeLsum": 0.0317,
+      "eval_runtime": 9.5457,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 302
+    },
+    {
+      "epoch": 22.98,
+      "eval_gen_len": 12.0455,
+      "eval_loss": 11.860977172851562,
+      "eval_rouge1": 0.023,
+      "eval_rouge2": 0.0048,
+      "eval_rougeL": 0.0204,
+      "eval_rougeLsum": 0.0204,
+      "eval_runtime": 9.5524,
+      "eval_samples_per_second": 11.515,
+      "eval_steps_per_second": 1.466,
+      "step": 316
+    },
+    {
+      "epoch": 24.0,
+      "eval_gen_len": 10.8545,
+      "eval_loss": 11.155168533325195,
+      "eval_rouge1": 0.012,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0108,
+      "eval_rougeLsum": 0.0108,
+      "eval_runtime": 9.5834,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 330
+    },
+    {
+      "epoch": 24.95,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 10.512735366821289,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0035,
+      "eval_rougeLsum": 0.0036,
+      "eval_runtime": 9.613,
+      "eval_samples_per_second": 11.443,
+      "eval_steps_per_second": 1.456,
+      "step": 343
+    },
+    {
+      "epoch": 25.96,
+      "eval_gen_len": 11.6,
+      "eval_loss": 9.83348560333252,
+      "eval_rouge1": 0.0039,
+      "eval_rouge2": 0.0002,
+      "eval_rougeL": 0.0038,
+      "eval_rougeLsum": 0.0039,
+      "eval_runtime": 9.5253,
+      "eval_samples_per_second": 11.548,
+      "eval_steps_per_second": 1.47,
+      "step": 357
+    },
+    {
+      "epoch": 26.98,
+      "eval_gen_len": 13.0455,
+      "eval_loss": 9.216172218322754,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5441,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 371
+    },
+    {
+      "epoch": 28.0,
+      "eval_gen_len": 14.6818,
+      "eval_loss": 8.572382926940918,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6018,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 385
+    },
+    {
+      "epoch": 28.95,
+      "eval_gen_len": 15.2727,
+      "eval_loss": 8.037731170654297,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0009,
+      "eval_rougeLsum": 0.0009,
+      "eval_runtime": 9.5646,
+      "eval_samples_per_second": 11.501,
+      "eval_steps_per_second": 1.464,
+      "step": 398
+    },
+    {
+      "epoch": 29.96,
+      "eval_gen_len": 16.3909,
+      "eval_loss": 7.415070056915283,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5548,
+      "eval_samples_per_second": 11.513,
+      "eval_steps_per_second": 1.465,
+      "step": 412
+    },
+    {
+      "epoch": 30.98,
+      "eval_gen_len": 17.8364,
+      "eval_loss": 6.802865028381348,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5629,
+      "eval_samples_per_second": 11.503,
+      "eval_steps_per_second": 1.464,
+      "step": 426
+    },
+    {
+      "epoch": 32.0,
+      "eval_gen_len": 18.2818,
+      "eval_loss": 6.211207866668701,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 440
+    },
+    {
+      "epoch": 32.95,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.717328071594238,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.505,
+      "eval_samples_per_second": 11.573,
+      "eval_steps_per_second": 1.473,
+      "step": 453
+    },
+    {
+      "epoch": 33.96,
+      "eval_gen_len": 18.7091,
+      "eval_loss": 5.17288064956665,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5443,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 467
+    },
+    {
+      "epoch": 34.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.669548034667969,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4845,
+      "eval_samples_per_second": 11.598,
+      "eval_steps_per_second": 1.476,
+      "step": 481
+    },
+    {
+      "epoch": 36.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 4.216309547424316,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5515,
+      "eval_samples_per_second": 11.516,
+      "eval_steps_per_second": 1.466,
+      "step": 495
+    },
+    {
+      "epoch": 36.36,
+      "grad_norm": 5.376431465148926,
+      "learning_rate": 1.660854700854701e-05,
+      "loss": 14.4939,
+      "step": 500
+    },
+    {
+      "epoch": 36.95,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.8450570106506348,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.525,
+      "eval_steps_per_second": 1.467,
+      "step": 508
+    },
+    {
+      "epoch": 37.96,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.507812261581421,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5902,
+      "eval_samples_per_second": 11.47,
+      "eval_steps_per_second": 1.46,
+      "step": 522
+    },
+    {
+      "epoch": 38.98,
+      "eval_gen_len": 19.0,
+      "eval_loss": 3.231505870819092,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5074,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 536
+    },
+    {
+      "epoch": 40.0,
+      "eval_gen_len": 19.0,
+      "eval_loss": 2.9967288970947266,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5195,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 550
+    },
+    {
+      "epoch": 40.95,
+      "eval_gen_len": 18.9545,
+      "eval_loss": 2.8089849948883057,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5224,
+      "eval_samples_per_second": 11.552,
+      "eval_steps_per_second": 1.47,
+      "step": 563
+    },
+    {
+      "epoch": 41.96,
+      "eval_gen_len": 18.3727,
+      "eval_loss": 2.6384663581848145,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5129,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 577
+    },
+    {
+      "epoch": 42.98,
+      "eval_gen_len": 16.7273,
+      "eval_loss": 2.492598295211792,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5174,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 591
+    },
+    {
+      "epoch": 44.0,
+      "eval_gen_len": 11.9636,
+      "eval_loss": 2.3677501678466797,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.5796,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 605
+    },
+    {
+      "epoch": 44.95,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 2.2777955532073975,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6685,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 618
+    },
+    {
+      "epoch": 45.96,
+      "eval_gen_len": 7.9455,
+      "eval_loss": 2.198147773742676,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.585,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 632
+    },
+    {
+      "epoch": 46.98,
+      "eval_gen_len": 7.5909,
+      "eval_loss": 2.1306562423706055,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6008,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.458,
+      "step": 646
+    },
+    {
+      "epoch": 48.0,
+      "eval_gen_len": 7.4091,
+      "eval_loss": 2.0773117542266846,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.6506,
+      "eval_samples_per_second": 11.398,
+      "eval_steps_per_second": 1.451,
+      "step": 660
+    },
+    {
+      "epoch": 48.95,
+      "eval_gen_len": 7.2909,
+      "eval_loss": 2.036808729171753,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5097,
+      "eval_samples_per_second": 11.567,
+      "eval_steps_per_second": 1.472,
+      "step": 673
+    },
+    {
+      "epoch": 49.96,
+      "eval_gen_len": 6.8364,
+      "eval_loss": 1.9949748516082764,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6031,
+      "eval_samples_per_second": 11.455,
+      "eval_steps_per_second": 1.458,
+      "step": 687
+    },
+    {
+      "epoch": 50.98,
+      "eval_gen_len": 7.8273,
+      "eval_loss": 1.957520842552185,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 701
+    },
+    {
+      "epoch": 52.0,
+      "eval_gen_len": 7.5545,
+      "eval_loss": 1.9219788312911987,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5836,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 715
+    },
+    {
+      "epoch": 52.95,
+      "eval_gen_len": 7.5364,
+      "eval_loss": 1.8916202783584595,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6019,
+      "eval_samples_per_second": 11.456,
+      "eval_steps_per_second": 1.458,
+      "step": 728
+    },
+    {
+      "epoch": 53.96,
+      "eval_gen_len": 7.1182,
+      "eval_loss": 1.8674402236938477,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5024,
+      "eval_samples_per_second": 11.576,
+      "eval_steps_per_second": 1.473,
+      "step": 742
+    },
+    {
+      "epoch": 54.98,
+      "eval_gen_len": 7.0364,
+      "eval_loss": 1.846158742904663,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 756
+    },
+    {
+      "epoch": 56.0,
+      "eval_gen_len": 7.0,
+      "eval_loss": 1.827086329460144,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.591,
+      "eval_samples_per_second": 11.469,
+      "eval_steps_per_second": 1.46,
+      "step": 770
+    },
+    {
+      "epoch": 56.95,
+      "eval_gen_len": 7.5455,
+      "eval_loss": 1.8088210821151733,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.572,
+      "eval_samples_per_second": 11.492,
+      "eval_steps_per_second": 1.463,
+      "step": 783
+    },
+    {
+      "epoch": 57.96,
+      "eval_gen_len": 7.9,
+      "eval_loss": 1.789602279663086,
+      "eval_rouge1": 0.0001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0001,
+      "eval_rougeLsum": 0.0001,
+      "eval_runtime": 9.5837,
+      "eval_samples_per_second": 11.478,
+      "eval_steps_per_second": 1.461,
+      "step": 797
+    },
+    {
+      "epoch": 58.98,
+      "eval_gen_len": 8.2545,
+      "eval_loss": 1.7687013149261475,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6152,
+      "eval_samples_per_second": 11.44,
+      "eval_steps_per_second": 1.456,
+      "step": 811
+    },
+    {
+      "epoch": 60.0,
+      "eval_gen_len": 8.3636,
+      "eval_loss": 1.7496564388275146,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4902,
+      "eval_samples_per_second": 11.591,
+      "eval_steps_per_second": 1.475,
+      "step": 825
+    },
+    {
+      "epoch": 60.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.7332907915115356,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 838
+    },
+    {
+      "epoch": 61.96,
+      "eval_gen_len": 8.9,
+      "eval_loss": 1.7185932397842407,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4797,
+      "eval_samples_per_second": 11.604,
+      "eval_steps_per_second": 1.477,
+      "step": 852
+    },
+    {
+      "epoch": 62.98,
+      "eval_gen_len": 9.7545,
+      "eval_loss": 1.7047526836395264,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.618,
+      "eval_samples_per_second": 11.437,
+      "eval_steps_per_second": 1.456,
+      "step": 866
+    },
+    {
+      "epoch": 64.0,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 1.6921414136886597,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6264,
+      "eval_samples_per_second": 11.427,
+      "eval_steps_per_second": 1.454,
+      "step": 880
+    },
+    {
+      "epoch": 64.95,
+      "eval_gen_len": 9.6909,
+      "eval_loss": 1.6816327571868896,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5134,
+      "eval_samples_per_second": 11.563,
+      "eval_steps_per_second": 1.472,
+      "step": 893
+    },
+    {
+      "epoch": 65.96,
+      "eval_gen_len": 8.9545,
+      "eval_loss": 1.6697723865509033,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5506,
+      "eval_samples_per_second": 11.518,
+      "eval_steps_per_second": 1.466,
+      "step": 907
+    },
+    {
+      "epoch": 66.98,
+      "eval_gen_len": 9.6818,
+      "eval_loss": 1.6568113565444946,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 921
+    },
+    {
+      "epoch": 68.0,
+      "eval_gen_len": 9.9455,
+      "eval_loss": 1.6469463109970093,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4825,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 935
+    },
+    {
+      "epoch": 68.95,
+      "eval_gen_len": 9.3545,
+      "eval_loss": 1.6408612728118896,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5212,
+      "eval_samples_per_second": 11.553,
+      "eval_steps_per_second": 1.47,
+      "step": 948
+    },
+    {
+      "epoch": 69.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.6316603422164917,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4986,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 962
+    },
+    {
+      "epoch": 70.98,
+      "eval_gen_len": 9.7818,
+      "eval_loss": 1.623169183731079,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5276,
+      "eval_samples_per_second": 11.545,
+      "eval_steps_per_second": 1.469,
+      "step": 976
+    },
+    {
+      "epoch": 72.0,
+      "eval_gen_len": 10.0273,
+      "eval_loss": 1.6152759790420532,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5801,
+      "eval_samples_per_second": 11.482,
+      "eval_steps_per_second": 1.461,
+      "step": 990
+    },
+    {
+      "epoch": 72.73,
+      "grad_norm": 3.344996213912964,
+      "learning_rate": 1.3196581196581197e-05,
+      "loss": 2.6089,
+      "step": 1000
+    },
+    {
+      "epoch": 72.95,
+      "eval_gen_len": 9.1727,
+      "eval_loss": 1.6071548461914062,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.6124,
+      "eval_samples_per_second": 11.444,
+      "eval_steps_per_second": 1.456,
+      "step": 1003
+    },
+    {
+      "epoch": 73.96,
+      "eval_gen_len": 9.1545,
+      "eval_loss": 1.599768042564392,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.498,
+      "eval_samples_per_second": 11.581,
+      "eval_steps_per_second": 1.474,
+      "step": 1017
+    },
+    {
+      "epoch": 74.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5934444665908813,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5664,
+      "eval_samples_per_second": 11.499,
+      "eval_steps_per_second": 1.463,
+      "step": 1031
+    },
+    {
+      "epoch": 76.0,
+      "eval_gen_len": 10.4091,
+      "eval_loss": 1.5867650508880615,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.579,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.462,
+      "step": 1045
+    },
+    {
+      "epoch": 76.95,
+      "eval_gen_len": 10.3,
+      "eval_loss": 1.5827070474624634,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.4875,
+      "eval_samples_per_second": 11.594,
+      "eval_steps_per_second": 1.476,
+      "step": 1058
+    },
+    {
+      "epoch": 77.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.5748482942581177,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4782,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1072
+    },
+    {
+      "epoch": 78.98,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 1.5662298202514648,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4778,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1086
+    },
+    {
+      "epoch": 80.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.5585095882415771,
+      "eval_rouge1": 0.0003,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0003,
+      "eval_rougeLsum": 0.0003,
+      "eval_runtime": 9.4851,
+      "eval_samples_per_second": 11.597,
+      "eval_steps_per_second": 1.476,
+      "step": 1100
+    },
+    {
+      "epoch": 80.95,
+      "eval_gen_len": 10.1364,
+      "eval_loss": 1.5539778470993042,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6048,
+      "eval_samples_per_second": 11.453,
+      "eval_steps_per_second": 1.458,
+      "step": 1113
+    },
+    {
+      "epoch": 81.96,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.541092038154602,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.4829,
+      "eval_samples_per_second": 11.6,
+      "eval_steps_per_second": 1.476,
+      "step": 1127
+    },
+    {
+      "epoch": 82.98,
+      "eval_gen_len": 9.6091,
+      "eval_loss": 1.5330486297607422,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5558,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 1.465,
+      "step": 1141
+    },
+    {
+      "epoch": 84.0,
+      "eval_gen_len": 9.0818,
+      "eval_loss": 1.5241070985794067,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6145,
+      "eval_samples_per_second": 11.441,
+      "eval_steps_per_second": 1.456,
+      "step": 1155
+    },
+    {
+      "epoch": 84.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.5192241668701172,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.4781,
+      "eval_samples_per_second": 11.606,
+      "eval_steps_per_second": 1.477,
+      "step": 1168
+    },
+    {
+      "epoch": 85.96,
+      "eval_gen_len": 9.5364,
+      "eval_loss": 1.5117179155349731,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5291,
+      "eval_samples_per_second": 11.544,
+      "eval_steps_per_second": 1.469,
+      "step": 1182
+    },
+    {
+      "epoch": 86.98,
+      "eval_gen_len": 9.4545,
+      "eval_loss": 1.4990766048431396,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6213,
+      "eval_samples_per_second": 11.433,
+      "eval_steps_per_second": 1.455,
+      "step": 1196
+    },
+    {
+      "epoch": 88.0,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 1.4878661632537842,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.4886,
+      "eval_samples_per_second": 11.593,
+      "eval_steps_per_second": 1.475,
+      "step": 1210
+    },
+    {
+      "epoch": 88.95,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.479432463645935,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5867,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1223
+    },
+    {
+      "epoch": 89.96,
+      "eval_gen_len": 9.3909,
+      "eval_loss": 1.471197247505188,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6139,
+      "eval_samples_per_second": 11.442,
+      "eval_steps_per_second": 1.456,
+      "step": 1237
+    },
+    {
+      "epoch": 90.98,
+      "eval_gen_len": 9.5,
+      "eval_loss": 1.4649511575698853,
+      "eval_rouge1": 0.0002,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0002,
+      "eval_rougeLsum": 0.0002,
+      "eval_runtime": 9.5947,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 1251
+    },
+    {
+      "epoch": 92.0,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.4548052549362183,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0016,
+      "eval_rougeLsum": 0.0017,
+      "eval_runtime": 9.6868,
+      "eval_samples_per_second": 11.356,
+      "eval_steps_per_second": 1.445,
+      "step": 1265
+    },
+    {
+      "epoch": 92.95,
+      "eval_gen_len": 9.3727,
+      "eval_loss": 1.444838285446167,
+      "eval_rouge1": 0.0005,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5071,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 1278
+    },
+    {
+      "epoch": 93.96,
+      "eval_gen_len": 9.6,
+      "eval_loss": 1.4365838766098022,
+      "eval_rouge1": 0.0014,
+      "eval_rouge2": 0.0004,
+      "eval_rougeL": 0.0014,
+      "eval_rougeLsum": 0.0015,
+      "eval_runtime": 9.5507,
+      "eval_samples_per_second": 11.517,
+      "eval_steps_per_second": 1.466,
+      "step": 1292
+    },
+    {
+      "epoch": 94.98,
+      "eval_gen_len": 9.3364,
+      "eval_loss": 1.4285393953323364,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6323,
+      "eval_samples_per_second": 11.42,
+      "eval_steps_per_second": 1.453,
+      "step": 1306
+    },
+    {
+      "epoch": 96.0,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.4242411851882935,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5163,
+      "eval_samples_per_second": 11.559,
+      "eval_steps_per_second": 1.471,
+      "step": 1320
+    },
+    {
+      "epoch": 96.95,
+      "eval_gen_len": 9.4,
+      "eval_loss": 1.4160754680633545,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1333
+    },
+    {
+      "epoch": 97.96,
+      "eval_gen_len": 9.4455,
+      "eval_loss": 1.4052343368530273,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6109,
+      "eval_samples_per_second": 11.445,
+      "eval_steps_per_second": 1.457,
+      "step": 1347
+    },
+    {
+      "epoch": 98.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.3928413391113281,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.6591,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.449,
+      "step": 1361
+    },
+    {
+      "epoch": 100.0,
+      "eval_gen_len": 9.5182,
+      "eval_loss": 1.3840864896774292,
+      "eval_rouge1": 0.0011,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0011,
+      "eval_rougeLsum": 0.0011,
+      "eval_runtime": 9.6661,
+      "eval_samples_per_second": 11.38,
+      "eval_steps_per_second": 1.448,
+      "step": 1375
+    },
+    {
+      "epoch": 100.95,
+      "eval_gen_len": 9.3,
+      "eval_loss": 1.381872296333313,
+      "eval_rouge1": 0.0006,
+      "eval_rouge2": 0.0001,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.6513,
+      "eval_samples_per_second": 11.397,
+      "eval_steps_per_second": 1.451,
+      "step": 1388
+    },
+    {
+      "epoch": 101.96,
+      "eval_gen_len": 9.3455,
+      "eval_loss": 1.37588632106781,
+      "eval_rouge1": 0.0004,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0004,
+      "eval_rougeLsum": 0.0004,
+      "eval_runtime": 9.5607,
+      "eval_samples_per_second": 11.505,
+      "eval_steps_per_second": 1.464,
+      "step": 1402
+    },
+    {
+      "epoch": 102.98,
+      "eval_gen_len": 9.2636,
+      "eval_loss": 1.3675447702407837,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.5449,
+      "eval_samples_per_second": 11.524,
+      "eval_steps_per_second": 1.467,
+      "step": 1416
+    },
+    {
+      "epoch": 104.0,
+      "eval_gen_len": 9.2455,
+      "eval_loss": 1.358955979347229,
+      "eval_rouge1": 0.0012,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0012,
+      "eval_rougeLsum": 0.0012,
+      "eval_runtime": 9.5868,
+      "eval_samples_per_second": 11.474,
+      "eval_steps_per_second": 1.46,
+      "step": 1430
+    },
+    {
+      "epoch": 104.95,
+      "eval_gen_len": 9.1455,
+      "eval_loss": 1.3501193523406982,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0005,
+      "eval_rougeLsum": 0.0005,
+      "eval_runtime": 9.6684,
+      "eval_samples_per_second": 11.377,
+      "eval_steps_per_second": 1.448,
+      "step": 1443
+    },
+    {
+      "epoch": 105.96,
+      "eval_gen_len": 9.1636,
+      "eval_loss": 1.344258189201355,
+      "eval_rouge1": 0.0007,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0007,
+      "eval_rougeLsum": 0.0007,
+      "eval_runtime": 9.5388,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 1457
+    },
+    {
+      "epoch": 106.98,
+      "eval_gen_len": 9.8,
+      "eval_loss": 1.3355817794799805,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.5263,
+      "eval_samples_per_second": 11.547,
+      "eval_steps_per_second": 1.47,
+      "step": 1471
+    },
+    {
+      "epoch": 108.0,
+      "eval_gen_len": 9.9182,
+      "eval_loss": 1.3305474519729614,
+      "eval_rouge1": 0.0008,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0008,
+      "eval_rougeLsum": 0.0008,
+      "eval_runtime": 9.6315,
+      "eval_samples_per_second": 11.421,
+      "eval_steps_per_second": 1.454,
+      "step": 1485
+    },
+    {
+      "epoch": 108.95,
+      "eval_gen_len": 10.1636,
+      "eval_loss": 1.3212946653366089,
+      "eval_rouge1": 0.0028,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0025,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.5797,
+      "eval_samples_per_second": 11.483,
+      "eval_steps_per_second": 1.461,
+      "step": 1498
+    },
+    {
+      "epoch": 109.09,
+      "grad_norm": 5.480063438415527,
+      "learning_rate": 9.784615384615387e-06,
+      "loss": 1.7753,
+      "step": 1500
+    },
+    {
+      "epoch": 109.96,
+      "eval_gen_len": 9.9091,
+      "eval_loss": 1.31065833568573,
+      "eval_rouge1": 0.0019,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0015,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.57,
+      "eval_samples_per_second": 11.494,
+      "eval_steps_per_second": 1.463,
+      "step": 1512
+    },
+    {
+      "epoch": 110.98,
+      "eval_gen_len": 10.2,
+      "eval_loss": 1.301637053489685,
+      "eval_rouge1": 0.0015,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0013,
+      "eval_runtime": 9.5009,
+      "eval_samples_per_second": 11.578,
+      "eval_steps_per_second": 1.474,
+      "step": 1526
+    },
+    {
+      "epoch": 112.0,
+      "eval_gen_len": 9.7091,
+      "eval_loss": 1.2922732830047607,
+      "eval_rouge1": 0.0014,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0014,
+      "eval_runtime": 9.5171,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 1540
+    },
+    {
+      "epoch": 112.95,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 1.2817051410675049,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.001,
+      "eval_rougeLsum": 0.001,
+      "eval_runtime": 9.5296,
+      "eval_samples_per_second": 11.543,
+      "eval_steps_per_second": 1.469,
+      "step": 1553
+    },
+    {
+      "epoch": 113.96,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 1.2726068496704102,
+      "eval_rouge1": 0.001,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.001,
+      "eval_rougeLsum": 0.001,
+      "eval_runtime": 9.6467,
+      "eval_samples_per_second": 11.403,
+      "eval_steps_per_second": 1.451,
+      "step": 1567
+    },
+    {
+      "epoch": 114.98,
+      "eval_gen_len": 9.5273,
+      "eval_loss": 1.2626111507415771,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0006,
+      "eval_rougeLsum": 0.0006,
+      "eval_runtime": 9.5006,
+      "eval_samples_per_second": 11.578,
+      "eval_steps_per_second": 1.474,
+      "step": 1581
+    },
+    {
+      "epoch": 116.0,
+      "eval_gen_len": 9.8,
+      "eval_loss": 1.2526050806045532,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0019,
+      "eval_rougeLsum": 0.0019,
+      "eval_runtime": 9.5945,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 1595
+    },
+    {
+      "epoch": 116.95,
+      "eval_gen_len": 9.6182,
+      "eval_loss": 1.2438002824783325,
+      "eval_rouge1": 0.0012,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0012,
+      "eval_rougeLsum": 0.0012,
+      "eval_runtime": 9.582,
+      "eval_samples_per_second": 11.48,
+      "eval_steps_per_second": 1.461,
+      "step": 1608
+    },
+    {
+      "epoch": 117.96,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.235589861869812,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0013,
+      "eval_runtime": 9.5074,
+      "eval_samples_per_second": 11.57,
+      "eval_steps_per_second": 1.473,
+      "step": 1622
+    },
+    {
+      "epoch": 118.98,
+      "eval_gen_len": 9.5727,
+      "eval_loss": 1.2265100479125977,
+      "eval_rouge1": 0.0017,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0017,
+      "eval_rougeLsum": 0.0017,
+      "eval_runtime": 9.6164,
+      "eval_samples_per_second": 11.439,
+      "eval_steps_per_second": 1.456,
+      "step": 1636
+    },
+    {
+      "epoch": 120.0,
+      "eval_gen_len": 9.7182,
+      "eval_loss": 1.21653151512146,
+      "eval_rouge1": 0.0013,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0011,
+      "eval_rougeLsum": 0.0011,
+      "eval_runtime": 9.5387,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 1650
+    },
+    {
+      "epoch": 120.95,
+      "eval_gen_len": 9.7182,
+      "eval_loss": 1.208518624305725,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0014,
+      "eval_rougeLsum": 0.0015,
+      "eval_runtime": 9.6008,
+      "eval_samples_per_second": 11.457,
+      "eval_steps_per_second": 1.458,
+      "step": 1663
+    },
+    {
+      "epoch": 121.96,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 1.1974164247512817,
+      "eval_rouge1": 0.0024,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0022,
+      "eval_rougeLsum": 0.0022,
+      "eval_runtime": 9.5182,
+      "eval_samples_per_second": 11.557,
+      "eval_steps_per_second": 1.471,
+      "step": 1677
+    },
+    {
+      "epoch": 122.98,
+      "eval_gen_len": 9.3273,
+      "eval_loss": 1.188578486442566,
+      "eval_rouge1": 0.0013,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0013,
+      "eval_rougeLsum": 0.0009,
+      "eval_runtime": 9.5875,
+      "eval_samples_per_second": 11.473,
+      "eval_steps_per_second": 1.46,
+      "step": 1691
+    },
+    {
+      "epoch": 124.0,
+      "eval_gen_len": 9.3727,
+      "eval_loss": 1.1796928644180298,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0018,
+      "eval_rougeLsum": 0.0018,
+      "eval_runtime": 9.5197,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1705
+    },
+    {
+      "epoch": 124.95,
+      "eval_gen_len": 9.4091,
+      "eval_loss": 1.1718236207962036,
+      "eval_rouge1": 0.0021,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0018,
+      "eval_rougeLsum": 0.0018,
+      "eval_runtime": 9.5197,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1718
+    },
+    {
+      "epoch": 125.96,
+      "eval_gen_len": 9.3364,
+      "eval_loss": 1.1624401807785034,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.5347,
+      "eval_samples_per_second": 11.537,
+      "eval_steps_per_second": 1.468,
+      "step": 1732
+    },
+    {
+      "epoch": 126.98,
+      "eval_gen_len": 9.6364,
+      "eval_loss": 1.1539288759231567,
+      "eval_rouge1": 0.0041,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0032,
+      "eval_rougeLsum": 0.0032,
+      "eval_runtime": 9.4835,
+      "eval_samples_per_second": 11.599,
+      "eval_steps_per_second": 1.476,
+      "step": 1746
+    },
+    {
+      "epoch": 128.0,
+      "eval_gen_len": 9.5364,
+      "eval_loss": 1.1447480916976929,
+      "eval_rouge1": 0.0018,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0017,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5263,
+      "eval_samples_per_second": 11.547,
+      "eval_steps_per_second": 1.47,
+      "step": 1760
+    },
+    {
+      "epoch": 128.95,
+      "eval_gen_len": 9.4545,
+      "eval_loss": 1.1359179019927979,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0021,
+      "eval_rougeLsum": 0.0021,
+      "eval_runtime": 9.5577,
+      "eval_samples_per_second": 11.509,
+      "eval_steps_per_second": 1.465,
+      "step": 1773
+    },
+    {
+      "epoch": 129.96,
+      "eval_gen_len": 9.3636,
+      "eval_loss": 1.1250239610671997,
+      "eval_rouge1": 0.0029,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0026,
+      "eval_rougeLsum": 0.0025,
+      "eval_runtime": 9.5118,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 1.472,
+      "step": 1787
+    },
+    {
+      "epoch": 130.98,
+      "eval_gen_len": 9.4364,
+      "eval_loss": 1.1156790256500244,
+      "eval_rouge1": 0.0034,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0031,
+      "eval_rougeLsum": 0.003,
+      "eval_runtime": 9.4869,
+      "eval_samples_per_second": 11.595,
+      "eval_steps_per_second": 1.476,
+      "step": 1801
+    },
+    {
+      "epoch": 132.0,
+      "eval_gen_len": 9.5182,
+      "eval_loss": 1.1065722703933716,
+      "eval_rouge1": 0.0029,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0027,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.6053,
+      "eval_samples_per_second": 11.452,
+      "eval_steps_per_second": 1.458,
+      "step": 1815
+    },
+    {
+      "epoch": 132.95,
+      "eval_gen_len": 9.6636,
+      "eval_loss": 1.0981847047805786,
+      "eval_rouge1": 0.0032,
+      "eval_rouge2": 0.0003,
+      "eval_rougeL": 0.0034,
+      "eval_rougeLsum": 0.0032,
+      "eval_runtime": 9.6558,
+      "eval_samples_per_second": 11.392,
+      "eval_steps_per_second": 1.45,
+      "step": 1828
+    },
+    {
+      "epoch": 133.96,
+      "eval_gen_len": 9.7273,
+      "eval_loss": 1.090613603591919,
+      "eval_rouge1": 0.0032,
+      "eval_rouge2": 0.0006,
+      "eval_rougeL": 0.0031,
+      "eval_rougeLsum": 0.0029,
+      "eval_runtime": 9.6549,
+      "eval_samples_per_second": 11.393,
+      "eval_steps_per_second": 1.45,
+      "step": 1842
+    },
+    {
+      "epoch": 134.98,
+      "eval_gen_len": 10.0818,
+      "eval_loss": 1.0842803716659546,
+      "eval_rouge1": 0.0061,
+      "eval_rouge2": 0.0008,
+      "eval_rougeL": 0.0052,
+      "eval_rougeLsum": 0.0052,
+      "eval_runtime": 9.4978,
+      "eval_samples_per_second": 11.582,
+      "eval_steps_per_second": 1.474,
+      "step": 1856
+    },
+    {
+      "epoch": 136.0,
+      "eval_gen_len": 9.5818,
+      "eval_loss": 1.075701117515564,
+      "eval_rouge1": 0.0046,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0042,
+      "eval_rougeLsum": 0.0042,
+      "eval_runtime": 9.6101,
+      "eval_samples_per_second": 11.446,
+      "eval_steps_per_second": 1.457,
+      "step": 1870
+    },
+    {
+      "epoch": 136.95,
+      "eval_gen_len": 9.8273,
+      "eval_loss": 1.0663608312606812,
+      "eval_rouge1": 0.0048,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0043,
+      "eval_rougeLsum": 0.0043,
+      "eval_runtime": 9.6501,
+      "eval_samples_per_second": 11.399,
+      "eval_steps_per_second": 1.451,
+      "step": 1883
+    },
+    {
+      "epoch": 137.96,
+      "eval_gen_len": 9.8545,
+      "eval_loss": 1.0555903911590576,
+      "eval_rouge1": 0.0055,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0046,
+      "eval_rougeLsum": 0.0045,
+      "eval_runtime": 9.5822,
+      "eval_samples_per_second": 11.48,
+      "eval_steps_per_second": 1.461,
+      "step": 1897
+    },
+    {
+      "epoch": 138.98,
+      "eval_gen_len": 9.9182,
+      "eval_loss": 1.0459803342819214,
+      "eval_rouge1": 0.0067,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.0063,
+      "eval_rougeLsum": 0.0062,
+      "eval_runtime": 9.659,
+      "eval_samples_per_second": 11.388,
+      "eval_steps_per_second": 1.449,
+      "step": 1911
+    },
+    {
+      "epoch": 140.0,
+      "eval_gen_len": 10.1636,
+      "eval_loss": 1.0374290943145752,
+      "eval_rouge1": 0.0067,
+      "eval_rouge2": 0.0017,
+      "eval_rougeL": 0.0062,
+      "eval_rougeLsum": 0.0061,
+      "eval_runtime": 9.5201,
+      "eval_samples_per_second": 11.555,
+      "eval_steps_per_second": 1.471,
+      "step": 1925
+    },
+    {
+      "epoch": 140.95,
+      "eval_gen_len": 9.8909,
+      "eval_loss": 1.0285921096801758,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.001,
+      "eval_rougeL": 0.0034,
+      "eval_rougeLsum": 0.0034,
+      "eval_runtime": 9.5989,
+      "eval_samples_per_second": 11.46,
+      "eval_steps_per_second": 1.458,
+      "step": 1938
+    },
+    {
+      "epoch": 141.96,
+      "eval_gen_len": 9.6455,
+      "eval_loss": 1.0195242166519165,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0027,
+      "eval_runtime": 9.5173,
+      "eval_samples_per_second": 11.558,
+      "eval_steps_per_second": 1.471,
+      "step": 1952
+    },
+    {
+      "epoch": 142.98,
+      "eval_gen_len": 9.8182,
+      "eval_loss": 1.0105475187301636,
+      "eval_rouge1": 0.0031,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5853,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 1966
+    },
+    {
+      "epoch": 144.0,
+      "eval_gen_len": 9.5091,
+      "eval_loss": 1.001856803894043,
+      "eval_rouge1": 0.0025,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0022,
+      "eval_rougeLsum": 0.002,
+      "eval_runtime": 9.5828,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 1980
+    },
+    {
+      "epoch": 144.95,
+      "eval_gen_len": 9.6909,
+      "eval_loss": 0.9937859773635864,
+      "eval_rouge1": 0.0023,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.5054,
+      "eval_samples_per_second": 11.572,
+      "eval_steps_per_second": 1.473,
+      "step": 1993
+    },
+    {
+      "epoch": 145.45,
+      "grad_norm": 3.3901820182800293,
+      "learning_rate": 6.365811965811967e-06,
+      "loss": 1.4532,
+      "step": 2000
+    },
+    {
+      "epoch": 145.96,
+      "eval_gen_len": 9.4182,
+      "eval_loss": 0.985722541809082,
+      "eval_rouge1": 0.0023,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.5248,
+      "eval_samples_per_second": 11.549,
+      "eval_steps_per_second": 1.47,
+      "step": 2007
+    },
+    {
+      "epoch": 146.98,
+      "eval_gen_len": 9.6818,
+      "eval_loss": 0.978095531463623,
+      "eval_rouge1": 0.0028,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5123,
+      "eval_samples_per_second": 11.564,
+      "eval_steps_per_second": 1.472,
+      "step": 2021
+    },
+    {
+      "epoch": 148.0,
+      "eval_gen_len": 9.7636,
+      "eval_loss": 0.9693424105644226,
+      "eval_rouge1": 0.0023,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0023,
+      "eval_rougeLsum": 0.0023,
+      "eval_runtime": 9.6266,
+      "eval_samples_per_second": 11.427,
+      "eval_steps_per_second": 1.454,
+      "step": 2035
+    },
+    {
+      "epoch": 148.95,
+      "eval_gen_len": 9.7545,
+      "eval_loss": 0.9614344835281372,
+      "eval_rouge1": 0.0016,
+      "eval_rouge2": 0.0002,
+      "eval_rougeL": 0.0017,
+      "eval_rougeLsum": 0.0016,
+      "eval_runtime": 9.5312,
+      "eval_samples_per_second": 11.541,
+      "eval_steps_per_second": 1.469,
+      "step": 2048
+    },
+    {
+      "epoch": 149.96,
+      "eval_gen_len": 9.7545,
+      "eval_loss": 0.9523000121116638,
+      "eval_rouge1": 0.0025,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0026,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5972,
+      "eval_samples_per_second": 11.462,
+      "eval_steps_per_second": 1.459,
+      "step": 2062
+    },
+    {
+      "epoch": 150.98,
+      "eval_gen_len": 9.7,
+      "eval_loss": 0.9436053037643433,
+      "eval_rouge1": 0.0009,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0009,
+      "eval_rougeLsum": 0.001,
+      "eval_runtime": 9.5824,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 2076
+    },
+    {
+      "epoch": 152.0,
+      "eval_gen_len": 9.8,
+      "eval_loss": 0.9361644983291626,
+      "eval_rouge1": 0.0024,
+      "eval_rouge2": 0.0009,
+      "eval_rougeL": 0.0024,
+      "eval_rougeLsum": 0.0024,
+      "eval_runtime": 9.5387,
+      "eval_samples_per_second": 11.532,
+      "eval_steps_per_second": 1.468,
+      "step": 2090
+    },
+    {
+      "epoch": 152.95,
+      "eval_gen_len": 9.8091,
+      "eval_loss": 0.9287785887718201,
+      "eval_rouge1": 0.0028,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5888,
+      "eval_samples_per_second": 11.472,
+      "eval_steps_per_second": 1.46,
+      "step": 2103
+    },
+    {
+      "epoch": 153.96,
+      "eval_gen_len": 9.9273,
+      "eval_loss": 0.9205007553100586,
+      "eval_rouge1": 0.0036,
+      "eval_rouge2": 0.0013,
+      "eval_rougeL": 0.0036,
+      "eval_rougeLsum": 0.0036,
+      "eval_runtime": 9.5824,
+      "eval_samples_per_second": 11.479,
+      "eval_steps_per_second": 1.461,
+      "step": 2117
+    },
+    {
+      "epoch": 154.98,
+      "eval_gen_len": 10.1,
+      "eval_loss": 0.9119426608085632,
+      "eval_rouge1": 0.0037,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0038,
+      "eval_rougeLsum": 0.0037,
+      "eval_runtime": 9.5407,
+      "eval_samples_per_second": 11.53,
+      "eval_steps_per_second": 1.467,
+      "step": 2131
+    },
+    {
+      "epoch": 156.0,
+      "eval_gen_len": 9.9364,
+      "eval_loss": 0.9043306112289429,
+      "eval_rouge1": 0.0034,
+      "eval_rouge2": 0.0011,
+      "eval_rougeL": 0.0034,
+      "eval_rougeLsum": 0.0034,
+      "eval_runtime": 9.5334,
+      "eval_samples_per_second": 11.538,
+      "eval_steps_per_second": 1.469,
+      "step": 2145
+    },
+    {
+      "epoch": 156.95,
+      "eval_gen_len": 9.7818,
+      "eval_loss": 0.8976907730102539,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.003,
+      "eval_rougeLsum": 0.0031,
+      "eval_runtime": 9.5568,
+      "eval_samples_per_second": 11.51,
+      "eval_steps_per_second": 1.465,
+      "step": 2158
+    },
+    {
+      "epoch": 157.96,
+      "eval_gen_len": 9.7364,
+      "eval_loss": 0.8908756971359253,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0007,
+      "eval_rougeL": 0.003,
+      "eval_rougeLsum": 0.0031,
+      "eval_runtime": 9.5534,
+      "eval_samples_per_second": 11.514,
+      "eval_steps_per_second": 1.465,
+      "step": 2172
+    },
+    {
+      "epoch": 158.98,
+      "eval_gen_len": 9.6273,
+      "eval_loss": 0.8828199505805969,
+      "eval_rouge1": 0.0017,
+      "eval_rouge2": 0.0002,
+      "eval_rougeL": 0.002,
+      "eval_rougeLsum": 0.0019,
+      "eval_runtime": 9.5064,
+      "eval_samples_per_second": 11.571,
+      "eval_steps_per_second": 1.473,
+      "step": 2186
+    },
+    {
+      "epoch": 160.0,
+      "eval_gen_len": 9.8273,
+      "eval_loss": 0.8748722076416016,
+      "eval_rouge1": 0.0045,
+      "eval_rouge2": 0.0015,
+      "eval_rougeL": 0.0036,
+      "eval_rougeLsum": 0.0036,
+      "eval_runtime": 9.6814,
+      "eval_samples_per_second": 11.362,
+      "eval_steps_per_second": 1.446,
+      "step": 2200
+    },
+    {
+      "epoch": 160.95,
+      "eval_gen_len": 9.9455,
+      "eval_loss": 0.8685693740844727,
+      "eval_rouge1": 0.0061,
+      "eval_rouge2": 0.0022,
+      "eval_rougeL": 0.0057,
+      "eval_rougeLsum": 0.0057,
+      "eval_runtime": 9.4971,
+      "eval_samples_per_second": 11.583,
+      "eval_steps_per_second": 1.474,
+      "step": 2213
+    },
+    {
+      "epoch": 161.96,
+      "eval_gen_len": 9.9364,
+      "eval_loss": 0.8622080087661743,
+      "eval_rouge1": 0.0056,
+      "eval_rouge2": 0.0017,
+      "eval_rougeL": 0.005,
+      "eval_rougeLsum": 0.0051,
+      "eval_runtime": 9.5035,
+      "eval_samples_per_second": 11.575,
+      "eval_steps_per_second": 1.473,
+      "step": 2227
+    },
+    {
+      "epoch": 162.98,
+      "eval_gen_len": 9.8636,
+      "eval_loss": 0.8555266261100769,
+      "eval_rouge1": 0.0049,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0046,
+      "eval_rougeLsum": 0.0047,
+      "eval_runtime": 9.5934,
+      "eval_samples_per_second": 11.466,
+      "eval_steps_per_second": 1.459,
+      "step": 2241
+    },
+    {
+      "epoch": 164.0,
+      "eval_gen_len": 9.9455,
+      "eval_loss": 0.8489392399787903,
+      "eval_rouge1": 0.0065,
+      "eval_rouge2": 0.0025,
+      "eval_rougeL": 0.0062,
+      "eval_rougeLsum": 0.0062,
+      "eval_runtime": 9.588,
+      "eval_samples_per_second": 11.473,
+      "eval_steps_per_second": 1.46,
+      "step": 2255
+    },
+    {
+      "epoch": 164.95,
+      "eval_gen_len": 10.1273,
+      "eval_loss": 0.8434127569198608,
+      "eval_rouge1": 0.0078,
+      "eval_rouge2": 0.0022,
+      "eval_rougeL": 0.0073,
+      "eval_rougeLsum": 0.0073,
+      "eval_runtime": 9.5692,
+      "eval_samples_per_second": 11.495,
+      "eval_steps_per_second": 1.463,
+      "step": 2268
+    },
+    {
+      "epoch": 165.96,
+      "eval_gen_len": 10.1,
+      "eval_loss": 0.8369239568710327,
+      "eval_rouge1": 0.0072,
+      "eval_rouge2": 0.0019,
+      "eval_rougeL": 0.0068,
+      "eval_rougeLsum": 0.0067,
+      "eval_runtime": 9.5983,
+      "eval_samples_per_second": 11.46,
+      "eval_steps_per_second": 1.459,
+      "step": 2282
+    },
+    {
+      "epoch": 166.98,
+      "eval_gen_len": 10.0636,
+      "eval_loss": 0.8303181529045105,
+      "eval_rouge1": 0.0068,
+      "eval_rouge2": 0.0022,
+      "eval_rougeL": 0.0062,
+      "eval_rougeLsum": 0.0061,
+      "eval_runtime": 9.5017,
+      "eval_samples_per_second": 11.577,
+      "eval_steps_per_second": 1.473,
+      "step": 2296
+    },
+    {
+      "epoch": 168.0,
+      "eval_gen_len": 9.9,
+      "eval_loss": 0.8243575096130371,
+      "eval_rouge1": 0.0044,
+      "eval_rouge2": 0.0013,
+      "eval_rougeL": 0.0039,
+      "eval_rougeLsum": 0.004,
+      "eval_runtime": 9.5856,
+      "eval_samples_per_second": 11.476,
+      "eval_steps_per_second": 1.461,
+      "step": 2310
+    },
+    {
+      "epoch": 168.95,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 0.8190615773200989,
+      "eval_rouge1": 0.0063,
+      "eval_rouge2": 0.0022,
+      "eval_rougeL": 0.0058,
+      "eval_rougeLsum": 0.0057,
+      "eval_runtime": 9.5114,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 1.472,
+      "step": 2323
+    },
+    {
+      "epoch": 169.96,
+      "eval_gen_len": 9.9818,
+      "eval_loss": 0.8129807114601135,
+      "eval_rouge1": 0.0054,
+      "eval_rouge2": 0.0017,
+      "eval_rougeL": 0.0047,
+      "eval_rougeLsum": 0.0047,
+      "eval_runtime": 9.625,
+      "eval_samples_per_second": 11.429,
+      "eval_steps_per_second": 1.455,
+      "step": 2337
+    },
+    {
+      "epoch": 170.98,
+      "eval_gen_len": 9.9727,
+      "eval_loss": 0.8074091672897339,
+      "eval_rouge1": 0.0059,
+      "eval_rouge2": 0.0017,
+      "eval_rougeL": 0.0052,
+      "eval_rougeLsum": 0.0052,
+      "eval_runtime": 9.5111,
+      "eval_samples_per_second": 11.565,
+      "eval_steps_per_second": 1.472,
+      "step": 2351
+    },
+    {
+      "epoch": 172.0,
+      "eval_gen_len": 9.9,
+      "eval_loss": 0.8017935752868652,
+      "eval_rouge1": 0.0045,
+      "eval_rouge2": 0.0008,
+      "eval_rougeL": 0.0038,
+      "eval_rougeLsum": 0.0039,
+      "eval_runtime": 9.5064,
+      "eval_samples_per_second": 11.571,
+      "eval_steps_per_second": 1.473,
+      "step": 2365
+    },
+    {
+      "epoch": 172.95,
+      "eval_gen_len": 9.7091,
+      "eval_loss": 0.7968164086341858,
+      "eval_rouge1": 0.0031,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0027,
+      "eval_rougeLsum": 0.0026,
+      "eval_runtime": 9.5948,
+      "eval_samples_per_second": 11.465,
+      "eval_steps_per_second": 1.459,
+      "step": 2378
+    },
+    {
+      "epoch": 173.96,
+      "eval_gen_len": 9.7364,
+      "eval_loss": 0.7917037010192871,
+      "eval_rouge1": 0.0025,
+      "eval_rouge2": 0.0005,
+      "eval_rougeL": 0.0022,
+      "eval_rougeLsum": 0.0022,
+      "eval_runtime": 9.636,
+      "eval_samples_per_second": 11.416,
+      "eval_steps_per_second": 1.453,
+      "step": 2392
+    },
+    {
+      "epoch": 174.98,
+      "eval_gen_len": 9.7455,
+      "eval_loss": 0.787342369556427,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0027,
+      "eval_rougeLsum": 0.0027,
+      "eval_runtime": 9.5895,
+      "eval_samples_per_second": 11.471,
+      "eval_steps_per_second": 1.46,
+      "step": 2406
+    },
+    {
+      "epoch": 176.0,
+      "eval_gen_len": 9.7,
+      "eval_loss": 0.7829388976097107,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.5727,
+      "eval_samples_per_second": 11.491,
+      "eval_steps_per_second": 1.462,
+      "step": 2420
+    },
+    {
+      "epoch": 176.95,
+      "eval_gen_len": 9.6091,
+      "eval_loss": 0.7783145904541016,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.6033,
+      "eval_samples_per_second": 11.454,
+      "eval_steps_per_second": 1.458,
+      "step": 2433
+    },
+    {
+      "epoch": 177.96,
+      "eval_gen_len": 9.7091,
+      "eval_loss": 0.7735804319381714,
+      "eval_rouge1": 0.0033,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.7017,
+      "eval_samples_per_second": 11.338,
+      "eval_steps_per_second": 1.443,
+      "step": 2447
+    },
+    {
+      "epoch": 178.98,
+      "eval_gen_len": 9.6364,
+      "eval_loss": 0.7691650986671448,
+      "eval_rouge1": 0.0026,
+      "eval_rouge2": 0.0016,
+      "eval_rougeL": 0.0028,
+      "eval_rougeLsum": 0.0028,
+      "eval_runtime": 9.6163,
+      "eval_samples_per_second": 11.439,
+      "eval_steps_per_second": 1.456,
+      "step": 2461
+    },
+    {
+      "epoch": 180.0,
+      "eval_gen_len": 9.4818,
+      "eval_loss": 0.7652955055236816,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.5613,
+      "eval_samples_per_second": 11.505,
+      "eval_steps_per_second": 1.464,
+      "step": 2475
+    },
+    {
+      "epoch": 180.95,
+      "eval_gen_len": 9.4818,
+      "eval_loss": 0.7611756920814514,
+      "eval_rouge1": 0.0,
+      "eval_rouge2": 0.0,
+      "eval_rougeL": 0.0,
+      "eval_rougeLsum": 0.0,
+      "eval_runtime": 9.6858,
+      "eval_samples_per_second": 11.357,
+      "eval_steps_per_second": 1.445,
+      "step": 2488
+    },
+    {
+      "epoch": 181.82,
+      "grad_norm": 1.818055272102356,
+      "learning_rate": 2.9470085470085475e-06,
+      "loss": 1.1581,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2925,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 225,
+  "save_steps": 500,
+  "total_flos": 9.676695641731891e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa417b6b216c589bddc528e9d4e9c81b5edc8c24a516e2f555101dee203aa64c
+size 5048

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65bbdef5b451c7fc345f152a8dcbbf6dde937a1110be55ff2cf5bd860b701a97
+oid sha256:fa417b6b216c589bddc528e9d4e9c81b5edc8c24a516e2f555101dee203aa64c
 size 5048